diff --git a/.gitattributes b/.gitattributes index ca022236d266ca63adf9681fa1e931c35cdae380..08b37219b2341cecf74ab64ff472cc01e610cccb 100644 --- a/.gitattributes +++ b/.gitattributes @@ -63,3 +63,210 @@ eval/onestep_long_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs eval/onestep_long_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text eval/onestep_long_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text eval/onestep_long_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/eval/bsp10_L0_latency_s1000/eval_info.json b/eval/bsp10_L0_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..28a5e8d1529962812037a069ace6c0fecfde29b6 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.99937175879365, + 19.99926372569403, + 19.999186143948627, + 19.99933107425, + 19.99931373365846, + 5.212845627631346, + 2.3292957187296386, + 0.21863772075889365, + 19.999348841247823, + 5.48575396175766, + 19.998560738003125, + 20.000124340155637, + 20.000449937877406, + 19.99942296901166, + 19.998813395962753, + 19.99969146877599, + 19.9988475858818, + 19.999476526551554, + 19.999456975116477, + 19.99844355268134, + 19.998779614174268, + 19.998631119166415, + 19.999160477330538, + 19.999665839034755, + 19.99979742754568, + 19.999378819449287, + 19.999741543239193, + 19.998804131560927, + 20.000563191036036, + 19.998851338022916, + 19.99879684881501, + 19.99901196450118, + 19.999991432111646, + 20.00024344461766, + 19.998844583807823, + 19.99987191031949, + 20.000311971511085, + 19.998703404946017, + 19.998908512053337, + 19.999565548663995, + 19.999817206134328, + 19.999973440247615, + 20.00062965221869, + 19.99926295814083, + 19.99865714865618, + 19.999793933199477, + 19.99988151055804, + 0.3849898855339662, + 19.99981131572423, + 19.999705875829072, + 19.99906400318566, + 19.9992428663852, + 19.999607332839734, + 20.000958891930917, + 19.998529983261903, + 19.998861638923536, + 19.99952638965153, + 19.99918100397128, + 20.00009538966656, + 19.999681545952903, + 19.999198643746958, + 19.999075583012882, + 7.235109229359157, + 19.99982949831307, + 19.99858060689092, + 20.000339053977587, + 19.99946564656422, + 19.99931725751422, + 19.99938151995769, + 19.999521471195596, + 19.999926320440448, + 19.999329603654285, + 19.99983066891353, + 5.5027791669839345, + 19.999347409109365, + 20.000713258535164, + 20.000944689719866, + 19.999424914420217, + 5.178682156287807, + 19.99947190703306, + 0.43509706367703505, + 19.998603442128374, + 20.000265528293767, + 19.999091089311776, + 19.99923159031522, + 20.001517281033795, + 19.999528879640657, + 19.998524442659477, + 19.99904608640668, + 19.99907036846048, + 19.999133342447937, + 19.99990421592954, + 19.998812750536416, + 20.00046053101019, + 19.999640439052044, + 5.202259958673804, + 19.999330643219256, + 20.000884828202114, + 19.99946935394517 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5163967229462807, + 1.7301485357975501, + 1.2323737867272433, + 10.0, + 1.5773484363369783, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.621161740740644, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 6.902969625697037, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5640332799844243, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5661363396407966, + 10.0, + 1.6523889914729397, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5371417552309514, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + true, + false, + false, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 100.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 96.0, + "pc_picked_top": 94.0, + "pc_nested_top": 90.0, + "pc_released_top": 90.0 + }, + "n_episodes": 100, + "n_success": 90, + "pc_success": 90.0, + "pc_success_ci95": [ + 82.56343384950866, + 94.47708629393249 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.371398720052124, + "avg_max_reward": 9.20900099214575, + "pc_success": 90.0, + "n_episodes": 100, + "n_success": 90, + "pc_success_ci95": [ + 82.56343384950866, + 94.47708629393249 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 100.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 96.0, + "pc_picked_top": 94.0, + "pc_nested_top": 90.0, + "pc_released_top": 90.0 + } + }, + "overall": { + "avg_sum_reward": 18.371398720052124, + "avg_max_reward": 9.20900099214575, + "pc_success": 90.0, + "n_episodes": 100, + "n_success": 90, + "pc_success_ci95": [ + 82.56343384950866, + 94.47708629393249 + ], + "eval_s": 1700.064938545227, + "eval_ep_s": 17.00064939022064, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 100.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 96.0, + "pc_picked_top": 94.0, + "pc_nested_top": 90.0, + "pc_released_top": 90.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a94bf6dbc3dd49046855ad533f38de67a266c60d --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef1ebe00a65c203cc115da28f46e7bf19bbe745184ced9c003f1457614c6b5b +size 473711 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b37eb6a7778c70e0ad37388d78668e2bbd93b2a4 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94655071d2d80589bfc3bc9eab441733b01fd6c1964f2e8f657c8fb192a9c9e6 +size 401668 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e3ef99c1e7e9b8050df2763a56883b28541fa986 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:953243e854cdc63c96dee1ba265622fb268dfd0d8695df33e05c086be164e541 +size 479004 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fc51691abd6fd539306771d9bfc9bc71fc7fad5e --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ca5f8ac1090b1f646074cc896c3390595aee231fcf10327c6261d1c09e3181 +size 464656 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9a23be0e7d51abf18b136746a9d4f3e33c1cae90 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a758c42d5710c085a988414494912354705cc54d71d87bb0838b3ee7cac9b1 +size 465671 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4e262119a7e9a423b73a3adbd9c33dc528dfe112 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e055b382c0de64c0bcbe0704be22021c18bba7ab70a706e93cd0e0bbd00435 +size 470759 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5be8784fd700c5177efd9434206d2cef3a252f26 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91e48665bc3baa14a4ced63ccd560259b0e65b6e4969f9124ccc3dac27e26ea +size 909892 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5ac480284bf2d855c76a42580c7b0a4a02ab628c --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668a00554e80fd67dc72a53cda92b923a5884f3c54185ee9b2e75664e4a771e5 +size 923884 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ec5fa942b231136175c03225b5909d56ee000ad8 --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5842d040ec55111fcd7ab6e2cbd2dd720ae9556ad0c5ed0914d2d88754d79aea +size 930871 diff --git a/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7766d1908d5bc80923895bac7f6c2bfb1c9a6e6f --- /dev/null +++ b/eval/bsp10_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7916595b53d82ccb3e731e659b5fcb628f5a4cbf83da070e34f3185cd42e8b6 +size 435496 diff --git a/eval/bsp10_L0_latency_s1001/eval_info.json b/eval/bsp10_L0_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..c095ff985174c897f1b7338e4cfbe486f1f02be1 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.999376173980398, + 19.999260996680878, + 19.99918614395783, + 19.999187752776603, + 19.999329399450097, + 19.998960604256602, + 19.999358418186816, + 20.000919642987565, + 19.999355275229547, + 19.999290942134586, + 19.99856537112195, + 20.000079951805773, + 20.000445775392972, + 19.9994189850642, + 19.999048399133365, + 19.999689910303804, + 19.998877383741505, + 19.999538019485634, + 19.998809129351322, + 19.999918778533313, + 19.998779613009333, + 19.998623367177323, + 19.999150829999298, + 19.99921522030574, + 19.999691588883756, + 19.99937544060903, + 19.999776223119575, + 19.99880413156093, + 20.00063215536691, + 19.998860082267353, + 19.999467187764157, + 19.999014402603017, + 5.482752555136477, + 1.6942927025327172, + 19.998585489611028, + 19.99993474371591, + 20.000301549948247, + 20.000779692554914, + 19.99890184338625, + 19.999548845466673, + 19.999819546686716, + 19.99990101372284, + 20.000682014718095, + 19.999262958140825, + 5.029851498596934, + 19.999793946389524, + 19.999845414927904, + 19.999990973322483, + 19.999816104295018, + 5.203326117024379, + 19.99906400570221, + 19.99933114563234, + 19.99963242274555, + 5.294505498642671, + 19.998531547219567, + 19.99881026825133, + 19.99955091019455, + 9.999181003971282, + 20.000094911824785, + 19.9996821229889, + 19.999198644424727, + 19.99905242622762, + 5.283672517181614, + 19.999825397105084, + 19.998962945475764, + 20.000404706861413, + 19.998883216606224, + 19.99937626985674, + 19.99937764379687, + 7.069353224049227, + 19.999902816054746, + 19.999329601871572, + 0.19675173109628796, + 20.00028784558642, + 19.999347408387052, + 20.000662342268647, + 0.3063372965216895, + 19.99942490606348, + 0.5395012106991001, + 19.99944301127642, + 0.15200108692404646, + 19.9985994903572, + 0.24810795873928337, + 19.99911848621343, + 5.008584923500872, + 20.001544872679226, + 0.5138773081005639, + 20.00033850246389, + 19.999046089488623, + 19.999290027768144, + 19.999125354876668, + 19.999275900800882, + 19.99881672770401, + 20.000393814376245, + 19.999638540549874, + 19.999312897145064, + 19.999338792924178, + 19.99837176591066, + 19.999437427318043 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5606845614064762, + 1.1842185031684265, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 4.574787176762244, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5732611903872278, + 10.0, + 10.0, + 10.0, + 1.5429847267427614, + 10.0, + 10.0, + 10.0, + 1.679353078203056, + 10.0, + 10.0, + 10.0, + 10.0, + 4.733068350862281, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.6150518655883017, + 10.0, + 10.0, + 1.2901808667982575, + 10.0, + 10.0, + 10.0, + 1.626006643443853, + 10.0, + 0.029618990716083204, + 10.0, + 1.5954333021992437, + 10.0, + 1.2422419268453897, + 10.0, + 1.543454869446323, + 10.0, + 0.027217292376140234, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + false, + true, + false, + true, + false, + true, + false, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 98.0, + "pc_nested_middle": 95.0, + "pc_released_middle": 92.0, + "pc_picked_top": 90.0, + "pc_nested_top": 86.0, + "pc_released_top": 86.0 + }, + "n_episodes": 100, + "n_success": 85, + "pc_success": 85.0, + "pc_success_ci95": [ + 76.71644040916765, + 90.69401471634336 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 17.519782939470748, + "avg_max_reward": 8.758175633449461, + "pc_success": 85.0, + "n_episodes": 100, + "n_success": 85, + "pc_success_ci95": [ + 76.71644040916765, + 90.69401471634336 + ], + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 95.0, + "pc_released_middle": 92.0, + "pc_picked_top": 90.0, + "pc_nested_top": 86.0, + "pc_released_top": 86.0 + } + }, + "overall": { + "avg_sum_reward": 17.519782939470748, + "avg_max_reward": 8.758175633449461, + "pc_success": 85.0, + "n_episodes": 100, + "n_success": 85, + "pc_success_ci95": [ + 76.71644040916765, + 90.69401471634336 + ], + "eval_s": 1685.4551723003387, + "eval_ep_s": 16.85455172777176, + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 95.0, + "pc_released_middle": 92.0, + "pc_picked_top": 90.0, + "pc_nested_top": 86.0, + "pc_released_top": 86.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5bc4463823eeba05305ccb3b631b3ff8ee319a9f --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe9024ac89eac8c3b2aa074b3281b1987b4e66eaeeda64aa9aff8efcac8100d +size 549953 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0a8466a120d616e04bb932c3789590761f2052f4 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e16402abe8e2b8f4664cc08bdb47592b63e343f3581603036e0ac3e609a5bcb2 +size 471409 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9b01aadabd1da6eb2ee05c871410612b5e5358e9 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6424e6e843b479d52b90b70ebb26be485f7d3137a79343f2641f81bd8fd625 +size 510231 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2faaadadf4870f7cfd8625177552c815e8a803f4 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:430c6417bfbb8a03ff9c8b22dce8f3dd5b2edffbaddb2240c6b29f5b1e85ad0d +size 469101 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4585cde10b10c3b2c6d698d084bbba964e13a099 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51d77f0aaa7c722b7196db11c780f78e80c22a707b1264ca5943e8cb320aa53 +size 551931 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0a8aa7c773ef44a04ec1f7d35a4200c384b1242a --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351f95ee83b084db1e1bd23d90068a90703a0549f420ae0542b0fcabdc6bf049 +size 490198 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d177d2fb0bd96f6b688741ad3a19a98b28c8489b --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3930fec3f75a63404ae921db8bb367b25723f842aa7b5ebcec39290d4eabfd94 +size 479369 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1f4053d9453efeceeb2e4d37b8dd872066b5c1b2 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456c87906a2b0454b6cc9e25e7189221599f650187e61cb2b0d1e77a936d7a8f +size 459777 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9584435089f90385cfb84e1a14d40a0f3f4e7232 --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b98edf1aafd90840a661bf3815b33cc182f9516746bc46d4eece031b087ef07 +size 433570 diff --git a/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..920e4e2373a100cde41631d1e829b8fe45093bcf --- /dev/null +++ b/eval/bsp10_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5357a53cb41425009dbb8b7b81d212a0024986f1c5cec36fb61d3fd0e08f9b4c +size 451281 diff --git a/eval/bsp10_L0_latency_s1002/eval_info.json b/eval/bsp10_L0_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..c3713f9b294c6b9f968c32f80a1bc9a940e5ba2e --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741735229193, + 19.999374296927176, + 19.99926265477228, + 19.999071268212482, + 19.999229236807665, + 19.99932161520764, + 19.999110429331488, + 19.999379525587436, + 19.999123076288665, + 19.999346220638692, + 19.999290942134582, + 19.998572190343438, + 20.000076863522608, + 20.00046821002737, + 19.999424772944607, + 19.999042827914977, + 19.9988585960841, + 19.998872852829287, + 19.999513509682505, + 19.999456975116477, + 19.99989838321038, + 19.998779613009336, + 19.99862640209165, + 0.24997028052374815, + 5.53731707069357, + 19.9997497686442, + 19.99937698677669, + 19.999886039469136, + 19.998804131560924, + 20.000578929767773, + 19.99880380316101, + 19.999484548159842, + 19.999025782153904, + 19.998512955990012, + 20.00025289145142, + 19.99882863286031, + 19.999857068218695, + 0.11380577481496079, + 5.480285003064723, + 19.998930685913212, + 19.999625998358194, + 5.183976407885597, + 19.999833772843054, + 20.00067187362191, + 19.999748505167734, + 19.998639490228257, + 19.99980517625852, + 19.99988717943094, + 0.009591819780485622, + 19.99980306395193, + 19.999615595373896, + 5.001568700054653, + 19.999331137343308, + 19.999609078346094, + 20.00091399476405, + 19.998587873462526, + 19.998878125089806, + 19.999261489342583, + 19.999636069606506, + 20.00010335266247, + 19.99968003373193, + 19.999198647057785, + 19.999063916722537, + 19.99878440395116, + 19.999828716642615, + 19.99901626549962, + 20.000324503428903, + 5.180735818901828, + 0.23946991240819926, + 19.999365550034806, + 19.999468651751098, + 19.999940559562486, + 19.999329602897177, + 19.99981591973016, + 19.998358758565946, + 19.99934740210795, + 20.00062358842805, + 20.000955127737083, + 19.999424911683846, + 19.999142207906445, + 19.999062375139317, + 20.001019474766217, + 19.998603929630487, + 20.00019521020829, + 19.999101069917728, + 19.999214246776212, + 19.999027210194427, + 19.999575305242104, + 20.000342433433747, + 19.999046095541683, + 19.99907036846048, + 19.99912934085948, + 19.999901021869427, + 19.998799704659746, + 20.000439635933464, + 19.999669178472537, + 19.99935608518141, + 19.99908330240632, + 20.000917100065355, + 19.999462382691434 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.026959105480430567, + 1.5560475264012168, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.697460207042782, + 4.679804218629282, + 10.0, + 10.0, + 1.5572845492814489, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 6.953974136942996, + 10.0, + 10.0, + 1.5314655958647847, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5392159062875066, + 0.024662997681548227, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 98.0, + "pc_nested_middle": 98.0, + "pc_released_middle": 97.0, + "pc_picked_top": 94.0, + "pc_nested_top": 91.0, + "pc_released_top": 91.0 + }, + "n_episodes": 100, + "n_success": 91, + "pc_success": 91.0, + "pc_success_ci95": [ + 83.7737871472837, + 95.19274599974348 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.469492912249105, + "avg_max_reward": 9.29566874243612, + "pc_success": 91.0, + "n_episodes": 100, + "n_success": 91, + "pc_success_ci95": [ + 83.7737871472837, + 95.19274599974348 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 98.0, + "pc_released_middle": 97.0, + "pc_picked_top": 94.0, + "pc_nested_top": 91.0, + "pc_released_top": 91.0 + } + }, + "overall": { + "avg_sum_reward": 18.469492912249105, + "avg_max_reward": 9.29566874243612, + "pc_success": 91.0, + "n_episodes": 100, + "n_success": 91, + "pc_success_ci95": [ + 83.7737871472837, + 95.19274599974348 + ], + "eval_s": 1351.6798753738403, + "eval_ep_s": 13.516798853874207, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 98.0, + "pc_released_middle": 97.0, + "pc_picked_top": 94.0, + "pc_nested_top": 91.0, + "pc_released_top": 91.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f538f4e9cfb9f6cb7ea1ea032f9c32aef05881e6 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fac8fc569dfffad5561a4f7b6148f1b938fe44feee17e53451a56da2e3e6d82 +size 507085 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..abdfef76d579e3749d67c268506641b5899363c4 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb6fd79a12a6ee156fbef85baeb8fc48d7c35f8791cd91d1154fc9b1b81532a +size 421922 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b55f8eb4abe54f3788a092782ed36cf2ef25f2a7 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56716d3efc20e9bbff7f04fdc62bf6bbdc435e00c160d05001b1029b6400474b +size 478159 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6fec2c94361da95588e331b761210b05d9b7b6c5 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d485f5ceedd03b467b7099a3fd2d44d040b4fb015617c9b5730b2097f0ccb8d6 +size 499950 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..67e3a4ca9653971525c63c0cf181994369a2ebab --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d91367d032b2c00b3c76add3af9c92c7929fa913e37bcdde81fdd35779933a21 +size 512025 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9baa10c3f2c6e2be7bf1835bfe72a9240a2dd4a7 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b4ffff22cb2fb913257d90532052f8861a1d189f67424d89748b81a9d5211f +size 486905 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b78fff20c5b5f90c93a4d7a145506c4ea7e4a4d5 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c6ffb3cf74f966f7c8dce5f56396dec3828edfe30e4e677721040ce8f8b48f +size 479860 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..09b055cfddc4aa180765749aa18c263aa4ea884c --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7835ab65f06dbaa1295e1f389c87cd94ba28c9d88a9946be97090a344dbc459b +size 424189 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..67618e7a98d3f885dc76adebef2b9513f190bd7b --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9625474f6db3b6c4d1628bf493b535acfc82ede137fc90894165e824e6305fc0 +size 503805 diff --git a/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0a65ad7ac9ffb0be2a62855bcdc77aee117600b8 --- /dev/null +++ b/eval/bsp10_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acddaa62385355edc9a57c5ddf3f4c603afbe423e486714f5f423aabf90d4e05 +size 437154 diff --git a/eval/bsp10_L0_s1002/eval_info.json b/eval/bsp10_L0_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b15a9f0a8855c808692d2a69e82d12655f406149 --- /dev/null +++ b/eval/bsp10_L0_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 20.00019657424091, + 19.999882618102184, + 19.999630292683772, + 19.999243593109316, + 19.999294164111355, + 19.99912093688704, + 19.99938173872588, + 20.000922809782956, + 19.999901041408844, + 19.999904542705018, + 19.998567074497227, + 20.00009100699564, + 20.00049621858611, + 19.99929530569687, + 19.999037595724438, + 19.999690922249158, + 19.998873825039308, + 19.99952886852026, + 20.000285861311166, + 19.999857458375857, + 19.998779613211596, + 19.99865523207572, + 19.99915082840394, + 20.000264990718463, + 20.000852674177658, + 19.999378899467878, + 19.999789023047654, + 19.998804131560927, + 20.000673090688903, + 19.99883652418931, + 20.000522504601125, + 19.99902428187997, + 19.999816944459592, + 20.00029663003278, + 19.998585489611024, + 19.99996500836765, + 20.00016346876133, + 20.000615534934944, + 19.99953575406335, + 19.999594274268244, + 19.999745707107284, + 19.999958666605913, + 20.00082428884079, + 19.999262958140832, + 19.99864185333056, + 19.9998220206046, + 20.00058377135788, + 19.99969497561434, + 19.99982524934122, + 19.999587208873944, + 19.999000677481927, + 19.99933114499962, + 19.99963991470303, + 20.000999629296068, + 19.99854748223223, + 19.999715730733854, + 19.999506078330313, + 20.00034815377883, + 20.000011447146175, + 19.999275931764544, + 19.99919864285656, + 19.999074012164797, + 19.999949724734442, + 19.99977525010676, + 20.000035746397117, + 20.00104485910113, + 20.000285294641383, + 19.999352864712975, + 19.999807431569145, + 19.99955759775258, + 19.999951130694058, + 19.999942526004176, + 19.99983158388754, + 20.000379525927254, + 19.99994514322203, + 20.000575060583074, + 20.000917003075763, + 19.99884254761623, + 20.000829091449663, + 19.999512350946578, + 20.00081132575476, + 19.99860479746871, + 20.000232198544193, + 19.99885672390546, + 19.9992204083565, + 20.0012925912119, + 19.99956248201608, + 20.000351308964476, + 19.999046095541686, + 19.999070368460483, + 19.999131603821702, + 20.000394549527666, + 19.999612251427124, + 20.000195021107558, + 19.999696592442042, + 19.999354949769234, + 19.99930249205286, + 20.000836655955375, + 19.999528352961583 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 100.0, + "pc_released_top": 100.0 + }, + "n_episodes": 100, + "n_success": 100, + "pc_success": 100.0, + "pc_success_ci95": [ + 96.30065017930143, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.99973939068524, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 100, + "n_success": 100, + "pc_success_ci95": [ + 96.30065017930143, + 100.0 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 100.0, + "pc_released_top": 100.0 + } + }, + "overall": { + "avg_sum_reward": 19.99973939068524, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 100, + "n_success": 100, + "pc_success_ci95": [ + 96.30065017930143, + 100.0 + ], + "eval_s": 2733.6283745765686, + "eval_ep_s": 27.336283752918245, + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 100.0, + "pc_released_top": 100.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9c052a709d79288a0d8c823a1cde7080cd435462 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d59c682d9dc08782a511ea13725e54bdf48c97495873755bb07f1460a1bbf3f8 +size 492177 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..22f7e6f3785a86e0f0f248d22f549ca658c90438 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafbdbba971492219c89e12b2f4730bd06803a946c219d338d4d5df4a36fd50a +size 422490 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..278cbfc6b72bc5681c7848c98af3a3ba02babe81 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d536b3e0235967e2ebd6555552485b1cb601d24a617515ee7918b7a164f11412 +size 492443 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..230330668efd104ce7f53d82ebae787afbfd1ab8 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fabd174d00e6e9b7ad59c6e657cad262a87d75b36567cc0911898979966567fe +size 466405 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..181e7a9acfa383dd19ec8a6b54daf045a77f89f8 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2016d2711dc663368df915fdad40e05e74577b52b9e7ba4a78247370158d5b +size 443276 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d39a7c781710579b025dd32c1224973b439f7f7f --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5767afd8f11253ddc723005d22d962c1c905b6f8b11ab4e7d87b6967ea3928 +size 491215 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7a3893cdb9aedfdf6ea016e1127bb29e65dfbc32 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f211bc35a65123f9f0af090987a2c24ba49051b768b0d8a24c4ae2d331cf1d2 +size 472219 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..eb85bdce0510a7e850f22511d78f4ed17fc89c51 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f9c125c381476f5a6106c9aa8ccbebc74fa821e6ba3b26136606c6cadc929a +size 422011 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9c7134364fcba97bb74af969a879a874c1f614f7 --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e0a64c194fe34f850bfeaf363c9cda1c3cee1fcedbb00ad2386dd9788407620 +size 413506 diff --git a/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..08b2ece861de5be2ab33ed5edf279faf53067eed --- /dev/null +++ b/eval/bsp10_L0_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f7c23de588b7a751d00ce2d31974010d3f78b6ef5e2b61c382bd9558ce02f0 +size 428807 diff --git a/eval/bsp10_L6_latency_s1000/eval_info.json b/eval/bsp10_L6_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6a7c41da8009b969b90662fff6bbf025e836d421 --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.188736965780882, + 5.381379589390468, + 5.243296188247126, + 19.999186144578168, + 19.999289729488666, + 19.999278195906143, + 19.9989606042566, + 19.99936345820116, + 20.001005913038664, + 19.99934813686317, + 5.240935557287363, + 19.998560169884833, + 20.00012763594772, + 5.447524166005708, + 19.999425603242585, + 5.315095835964403, + 19.999675211900644, + 19.99884426480895, + 19.9995159537207, + 0.48028261814038264, + 19.99997211033601, + 0.4763049436050305, + 19.998660922499216, + 19.99915082880547, + 0.10553008566143818, + 19.999733237993265, + 0.08018309800366996, + 19.999759089899346, + 5.223747336777347, + 20.0006425585549, + 0.25140233965340797, + 19.99947042202487, + 0.16869993258941218, + 19.99999024846513, + 20.000268541918203, + 0.23870385362014934, + 19.99994627927368, + 20.00029083288956, + 0.28499581958806686, + 19.998939261780315, + 19.99964735049408, + 6.878520853225426, + 0.21437848314743313, + 0.28404475392548, + 19.999870566253964, + 19.998635266831876, + 0.2314297607718676, + 5.357937002866841, + 20.000000126080824, + 19.999871342275327, + 0.452490773068415, + 19.999067125978076, + 0.11984648084382976, + 19.99960379737867, + 20.000910258412937, + 19.99852905318345, + 19.998767890801453, + 19.99949954429056, + 19.99961328322774, + 5.440892037323577, + 0.16930252768139875, + 19.9991983911312, + 19.999045763218206, + 19.99996605717331, + 5.183803596189293, + 19.99906499934324, + 20.000409570955572, + 19.999459277765514, + 19.998672921800697, + 19.999381036288284, + 5.412407452303535, + 19.99999185667815, + 5.438503843363731, + 9.999084323334246, + 20.00042842674851, + 19.999347409648262, + 20.00068531587947, + 5.42010504955017, + 19.999424123326254, + 19.99982410209751, + 5.338675585262992, + 0.2654059734919998, + 0.43594881682875997, + 5.224216740134324, + 5.217304874904116, + 19.999224161466728, + 5.449545062546334, + 19.99960030636243, + 0.35904848528465694, + 19.99904607876011, + 19.9992900169614, + 19.999132267308962, + 5.411417792320944, + 5.200512097511573, + 20.000642226926907, + 19.99965299325507, + 19.99936322967504, + 9.99908330240632, + 20.000856408104458, + 19.999495313972865 + ], + "max_rewards": [ + 1.5212821336880715, + 1.556946570042144, + 1.5633235815158015, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.574918602141803, + 10.0, + 10.0, + 1.546125296709302, + 10.0, + 1.5611472146918004, + 10.0, + 10.0, + 10.0, + 0.05576805159484377, + 10.0, + 1.1750051154379024, + 10.0, + 10.0, + 1.229307764709759, + 10.0, + 1.3213175719292716, + 10.0, + 1.55833987752258, + 10.0, + 1.0982878327337269, + 10.0, + 1.2477582618631422, + 10.0, + 10.0, + 1.1730372213386362, + 10.0, + 10.0, + 1.5602030650363041, + 10.0, + 10.0, + 1.5840048243369087, + 1.3087422860238411, + 7.049711517974522, + 10.0, + 10.0, + 1.2355249028596986, + 4.6700401908737454, + 10.0, + 10.0, + 1.1902502015857224, + 10.0, + 1.2251859790981032, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5683484918412693, + 1.2448161509355158, + 10.0, + 10.0, + 10.0, + 1.5772506946790672, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5370051214121736, + 10.0, + 1.503859213233008, + 1.626415258179528, + 10.0, + 10.0, + 10.0, + 1.5778850105254945, + 10.0, + 10.0, + 1.530365973442441, + 1.2325071136032562, + 1.2398612554652324, + 1.546312021500953, + 1.560756998940413, + 10.0, + 1.5664493602259624, + 10.0, + 1.5831508198768618, + 10.0, + 10.0, + 10.0, + 4.479355922035321, + 1.5553695642688155, + 10.0, + 10.0, + 10.0, + 1.674103174791687, + 10.0, + 10.0 + ], + "successes": [ + false, + false, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + false, + true, + true, + true, + false, + true, + false, + true, + true, + false, + true, + false, + true, + false, + true, + false, + true, + false, + true, + true, + false, + true, + true, + false, + true, + true, + false, + false, + false, + true, + true, + false, + false, + true, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + false, + false, + true, + true, + true, + false, + true, + true, + false, + false, + false, + false, + false, + true, + false, + true, + false, + true, + true, + true, + false, + false, + true, + true, + true, + false, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 89.0, + "pc_nested_middle": 86.0, + "pc_released_middle": 85.0, + "pc_picked_top": 69.0, + "pc_nested_top": 64.0, + "pc_released_top": 64.0 + }, + "n_episodes": 100, + "n_success": 61, + "pc_success": 61.0, + "pc_success_ci95": [ + 51.203017045840724, + 69.98312599360558 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 13.526053472149371, + "avg_max_reward": 6.766100402086646, + "pc_success": 61.0, + "n_episodes": 100, + "n_success": 61, + "pc_success_ci95": [ + 51.203017045840724, + 69.98312599360558 + ], + "video_paths": [ + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 89.0, + "pc_nested_middle": 86.0, + "pc_released_middle": 85.0, + "pc_picked_top": 69.0, + "pc_nested_top": 64.0, + "pc_released_top": 64.0 + } + }, + "overall": { + "avg_sum_reward": 13.526053472149371, + "avg_max_reward": 6.766100402086646, + "pc_success": 61.0, + "n_episodes": 100, + "n_success": 61, + "pc_success_ci95": [ + 51.203017045840724, + 69.98312599360558 + ], + "eval_s": 2143.471787929535, + "eval_ep_s": 21.43471788406372, + "video_paths": [ + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 89.0, + "pc_nested_middle": 86.0, + "pc_released_middle": 85.0, + "pc_picked_top": 69.0, + "pc_nested_top": 64.0, + "pc_released_top": 64.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3926b77d5d36e0f10680a41c24de6c51dc26d7fc --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6a358c92b3212ff54d7f0cdc7d4bc962e6a427c85d2d6495d3853ea2c05758 +size 960150 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b250d3fca2cc7fad3cc151a934cbd95ffee92580 --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e17e9ff5cebdc841a936eae357fe620d812b2e300182c9ed1a760a2cedc365c4 +size 906374 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..de313dc53616ec565c41e2f1dbfc011de98b47ea --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a35bf1e17abde5c57446d472cef1322c5aba40dbaab632cfb32ea80c010196a +size 1100114 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..63a46ee49e562fad6eb1f5e27b4254d201a681de --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a0169abb9986f289c578583527f6141f60b8e3da32d5c88d6fe5c335d51e87 +size 475887 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c01c5087b498c167388e83c6cfeea13dbea18f0e --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6cc311a6c79b473dbbf59d9b17e5f14ed6d6e238cd4a01a74df3b98d9d431b8 +size 535780 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..db6c1737b3c7553017b5d3548b0bfffdf5273f0a --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc257285efca9421cb9ad5baad5acd293802fd847c9c85fb83b5e24c0899f84 +size 504905 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..302ee1f69846da22f29ae65fd162b126f38e49d6 --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a77df6e0d93a14834cdaa33b84b1b04393c287fd07422027cf4524bd3672a1 +size 563926 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..35105a529f975888bb1e2eb9db6f0cd2739f3bef --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944c6a0a4f5102d4147509c51c0cc4670c8ea7f12b552fa5b5a656f65f35c4ee +size 431251 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..42600886bdf526b84c7fa018fb1a14549a5163ad --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16fab262eba626d6a4140668f28deb4e065b848a7311f9d7ac8768502290bdb +size 429761 diff --git a/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..facfab909a62323688102b53d96f31764652f428 --- /dev/null +++ b/eval/bsp10_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba729f7cf033514e7158913783ef71bb02fb5e4715fe8977978ee09a4822c1d +size 422199 diff --git a/eval/bsp10_L6_latency_s1001/eval_info.json b/eval/bsp10_L6_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0d9be9166c81f3844fc81ebba0af79b4a7886e8e --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 0.05624038009384691, + 0.061437155140103616, + 19.99926318059986, + 19.999187975772024, + 19.999277077840098, + 19.999282319406895, + 0.06343218336370693, + 5.073083981588372, + 20.001050148589314, + 19.99935245676199, + 19.99944395321251, + 5.241631649011221, + 20.000089561434756, + 0.2875738988197156, + 0.030277555892612273, + 19.999022455188513, + 5.2417648219899196, + 0.2919787360317836, + 0.3183904719691655, + 0.30322066732592257, + 0.25030313663976855, + 0.40169881550535325, + 5.095856756923947, + 5.125795060729372, + 0.050805845848075015, + 19.99974728451398, + 5.31431572004249, + 0.36323415694730254, + 9.998804131560929, + 5.300211814356434, + 19.998841847915976, + 5.433306380551047, + 19.999015553075324, + 20.00002831268526, + 20.00027961282343, + 0.42670154229945256, + 0.13656273794626095, + 5.260042537524793, + 5.4085120769232145, + 5.112305222757694, + 19.999620482384227, + 19.99980626641623, + 19.99991815197702, + 0.2793583092493982, + 19.99979873007073, + 19.998649689147346, + 19.999793946389524, + 19.999824845657713, + 19.999960843657874, + 5.418994580256257, + 19.99971783833131, + 5.324410717832413, + 5.416601403813396, + 0.33050689837154923, + 20.00090640537065, + 19.99854289263933, + 0.21157871976929254, + 0.10522651893268176, + 0.06724870433964902, + 0.3023625117436376, + 19.999682146045572, + 19.99919811184598, + 0.046388707019276554, + 19.9999885518963, + 0.22476567738884834, + 0.26939510423217694, + 20.00035345882199, + 0.058829450071711475, + 19.999346280252627, + 19.99939989494067, + 0.0322259621128097, + 5.140470585625646, + 19.99932960224011, + 5.2191856120444, + 20.000329836874585, + 19.99934740964826, + 20.000775325832947, + 0.25239447743239474, + 19.999423701280318, + 19.999766680603994, + 5.367646586757281, + 0.2772027948374537, + 19.998605812523127, + 20.000270390322562, + 0.07184502777703794, + 0.12489739356792118, + 20.001505314583554, + 19.999561468552272, + 0.21352321766333004, + 19.9990451823701, + 5.179147892290503, + 19.999134472893534, + 19.9999010213794, + 19.998816528203257, + 0.3930203414663932, + 19.999651421220072, + 9.99926020373648, + 19.999337954036623, + 20.000892745212738, + 19.999471380171048 + ], + "max_rewards": [ + 1.2659582601776567, + 1.2776506385191952, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3218306174790686, + 1.5680177181092319, + 10.0, + 10.0, + 10.0, + 1.5469410889332864, + 10.0, + 1.3521415287233827, + 1.30569285550244, + 10.0, + 1.560570110552475, + 1.2040598525703323, + 1.1016498393750522, + 1.1214350376924582, + 1.3826425774979643, + 1.1833015714735269, + 1.5702163551464319, + 1.5311280695088314, + 0.04473267664412539, + 10.0, + 1.5422874929626196, + 1.3310963821070971, + 1.7027343485862145, + 1.5666863976512055, + 10.0, + 1.5548532498854235, + 10.0, + 10.0, + 10.0, + 1.2182438462157368, + 0.051633903403259795, + 1.5737596442972266, + 1.567567845532773, + 1.5654332254878052, + 10.0, + 10.0, + 10.0, + 1.2449901011995412, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5661544352503254, + 10.0, + 1.5134954493460335, + 1.5531030044220893, + 1.1138722614642433, + 10.0, + 10.0, + 1.219548407020663, + 1.3470594939243714, + 1.3979247512092923, + 1.307398728327946, + 10.0, + 10.0, + 1.3511573096507399, + 10.0, + 1.3763146865368905, + 0.05374666310065901, + 10.0, + 0.043088000827399275, + 10.0, + 10.0, + 0.05431946307402569, + 1.5778942882633749, + 10.0, + 1.5970370643755643, + 10.0, + 10.0, + 10.0, + 1.2908935941871496, + 10.0, + 10.0, + 1.5457313697763784, + 0.04235598249175243, + 10.0, + 10.0, + 1.3197609578910172, + 1.3021161075605983, + 10.0, + 10.0, + 1.3240499267026422, + 10.0, + 1.5577829256126334, + 10.0, + 10.0, + 10.0, + 1.2994808002912088, + 10.0, + 1.6227466069005232, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + false, + false, + true, + true, + true, + true, + false, + false, + true, + true, + true, + false, + true, + false, + false, + true, + false, + false, + false, + false, + false, + false, + false, + false, + false, + true, + false, + false, + false, + false, + true, + false, + true, + true, + true, + false, + false, + false, + false, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + false, + false, + false, + true, + true, + false, + false, + false, + false, + true, + true, + false, + true, + false, + false, + true, + false, + true, + true, + false, + false, + true, + false, + true, + true, + true, + false, + true, + true, + false, + false, + true, + true, + false, + false, + true, + true, + false, + true, + false, + true, + true, + true, + false, + true, + false, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 76.0, + "pc_nested_middle": 69.0, + "pc_released_middle": 69.0, + "pc_picked_top": 53.0, + "pc_nested_top": 51.0, + "pc_released_top": 51.0 + }, + "n_episodes": 100, + "n_success": 49, + "pc_success": 49.0, + "pc_success_ci95": [ + 39.421998930441134, + 58.65198806597283 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 11.009575313597281, + "avg_max_reward": 5.536342875134418, + "pc_success": 49.0, + "n_episodes": 100, + "n_success": 49, + "pc_success_ci95": [ + 39.421998930441134, + 58.65198806597283 + ], + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 76.0, + "pc_nested_middle": 69.0, + "pc_released_middle": 69.0, + "pc_picked_top": 53.0, + "pc_nested_top": 51.0, + "pc_released_top": 51.0 + } + }, + "overall": { + "avg_sum_reward": 11.009575313597281, + "avg_max_reward": 5.536342875134418, + "pc_success": 49.0, + "n_episodes": 100, + "n_success": 49, + "pc_success_ci95": [ + 39.421998930441134, + 58.65198806597283 + ], + "eval_s": 1795.4770767688751, + "eval_ep_s": 17.954770774841307, + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 76.0, + "pc_nested_middle": 69.0, + "pc_released_middle": 69.0, + "pc_picked_top": 53.0, + "pc_nested_top": 51.0, + "pc_released_top": 51.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ce0162d50f197c9c884a7f1ef516975699124179 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af12dadfe4d12982227bf829f4790f8f06d21ce68ed77070b6d4287f5e63edff +size 794328 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e8cd9af4d092280a4405b0fdf5cf368281cf9eb7 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48b6aea69b461d990298df474a82472eb954dfca729ccbe6988a29258e02ca22 +size 895371 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e149dae9ed2380c55dcce80f01ab213dc0927202 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0754cac81a0d2d3ca6d1366738ab4196b2feba534f592df5e8d80b7be4df918b +size 484192 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b3733eecaf717284ea11db9933d13fd2caf81ded --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8ad5f993bb69b68abdae2dd1bcf6bad04989909fb5d69c4411a4a6652047a6 +size 501547 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b2220d798a8d93010f8351c655cf48a98bcbf356 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999e19bb25f162e764200e2238c17bf8872953a906d7b66e68eadd352097b890 +size 871484 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2ee57725da3e33939c5f32f7b507f72b870a7a9a --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703ca01de24e9320c6ed0b1ba712f04b249c13f4379dfd317d694d1b4add65f2 +size 507732 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2c56060b7163dd52fc8d0fbc1077318716e00105 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c405ce34c5880245a61f9ad3430f12ac08e6e009d3941b16a990d89a4d311b +size 930967 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c181517c67fb817666830353162021c5ec7df284 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af84b7efa03af9ae83cbc4530af87e28a2c44e16a497629d80eadfc38ce833f +size 935235 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3f44f54617f2df523fb77512558558025b32b8ad --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9368fd88615deb15c44ebe4bef8839a5cf82e6ac91e913ae6c402299680bd02 +size 435627 diff --git a/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b86c36bd3e0f6642d69eb80ca8ce332248ad9f07 --- /dev/null +++ b/eval/bsp10_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3144e89c4197d54c3aaa0f50ab68b3f15f493e4d5e32ce91a6f8a73c1fd10189 +size 429441 diff --git a/eval/bsp10_L6_latency_s1002/eval_info.json b/eval/bsp10_L6_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3673ff387e622a132466817ded9f4d0008302e32 --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741585172664, + 19.99936398412199, + 0.39685806805165635, + 19.9991908368627, + 19.999347335617088, + 19.99926612062584, + 0.043691517914664746, + 19.999383145325453, + 20.0009335622171, + 5.355547616843319, + 5.449063509274695, + 19.99856096651663, + 9.998774778236797, + 8.998768270132954, + 19.999419406464074, + 19.999017981522055, + 0.30379902765535594, + 5.291035161454522, + 19.999490437498622, + 19.999456950349952, + 19.999836073326232, + 19.99877961473548, + 19.998624217126462, + 0.4284324188581359, + 0.024083273242221925, + 19.999750067726342, + 19.99937544509277, + 0.4865097999636411, + 19.998926634653895, + 5.5107686423609525, + 19.99884712700055, + 0.14140328153237192, + 5.338715461913596, + 0.3230580287775696, + 20.000300425176253, + 19.99880623777876, + 19.99987640533426, + 5.200079965534218, + 0.372843857903726, + 19.998844074775132, + 19.999596138503726, + 5.470566643845352, + 19.999879937111224, + 5.4607064866312935, + 5.330453739796882, + 19.99842078638443, + 19.999793878538526, + 19.99986575380251, + 20.000027871514902, + 19.99981424518823, + 19.99967047496944, + 0.019669665967114836, + 19.99933113920555, + 0.3761384925562724, + 20.000979872062086, + 5.305149170885608, + 5.291716999210931, + 19.999586990429517, + 19.999630800647687, + 20.000111989189193, + 5.417325028733659, + 19.9991986380498, + 19.99905925569766, + 5.513850950119153, + 19.99981670214703, + 19.99897194932069, + 19.999279681370744, + 19.999456892220397, + 19.999356984577116, + 19.999378626906047, + 19.999554306472177, + 5.191412141688456, + 19.99932960556758, + 19.999832828717327, + 20.000372473769634, + 19.999347380626624, + 20.000675841188727, + 20.001062890395794, + 5.009924933241669, + 19.999760325483642, + 19.99945344907571, + 20.00101295366729, + 19.998617310624333, + 20.000199541092258, + 7.422249302871568, + 19.99921606648857, + 20.00151849855331, + 19.99955948630073, + 20.000388500816662, + 19.99905603221423, + 9.999070368460483, + 5.412110659800738, + 9.999275900800884, + 19.998808628090437, + 5.291529918909692, + 19.99962734502018, + 0.1037279632845558, + 19.999296067897806, + 0.27650833962369603, + 19.99948889174026 + ], + "max_rewards": [ + 10.0, + 10.0, + 1.1145333961647483, + 10.0, + 10.0, + 10.0, + 1.327349796855612, + 10.0, + 10.0, + 1.568943834400487, + 1.5619548994086963, + 10.0, + 1.6075775277579232, + 1.5531017235102045, + 10.0, + 10.0, + 0.051600758262620894, + 1.5495079624474037, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.1501134153189199, + 1.2445618725461578, + 10.0, + 10.0, + 1.2998903517153408, + 10.0, + 1.5676962152755896, + 10.0, + 0.04380135189212975, + 1.5506158970522714, + 1.388621981642764, + 10.0, + 10.0, + 10.0, + 4.993430881414547, + 1.317724813332896, + 10.0, + 10.0, + 1.5773855262017558, + 10.0, + 1.5345960703998123, + 1.5287603130784027, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.031136293726562014, + 10.0, + 1.125123420608844, + 10.0, + 1.5655131263919744, + 1.5684602293551695, + 10.0, + 10.0, + 10.0, + 4.502956511978812, + 10.0, + 10.0, + 1.5600689609561995, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 5.052736935970954, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5410668479494265, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5653446876126584, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5936986209619486, + 1.5576698502989408, + 1.5812171343643122, + 10.0, + 7.008577048207491, + 10.0, + 1.3033034568186084, + 10.0, + 4.720376443054523, + 10.0 + ], + "successes": [ + true, + true, + false, + true, + true, + true, + false, + true, + true, + false, + false, + true, + false, + false, + true, + true, + false, + false, + true, + true, + true, + true, + true, + false, + false, + true, + true, + false, + true, + false, + true, + false, + false, + false, + true, + true, + true, + false, + false, + true, + true, + false, + true, + false, + false, + true, + true, + true, + true, + true, + true, + false, + true, + false, + true, + false, + false, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + false, + false, + true, + false, + true, + false, + true, + false, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 92.0, + "pc_nested_middle": 88.0, + "pc_released_middle": 88.0, + "pc_picked_top": 75.0, + "pc_nested_top": 69.0, + "pc_released_top": 68.0 + }, + "n_episodes": 100, + "n_success": 65, + "pc_success": 65.0, + "pc_success_ci95": [ + 55.254443296887956, + 73.63575175690247 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 14.405273650527384, + "avg_max_reward": 7.158090181569347, + "pc_success": 65.0, + "n_episodes": 100, + "n_success": 65, + "pc_success_ci95": [ + 55.254443296887956, + 73.63575175690247 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 92.0, + "pc_nested_middle": 88.0, + "pc_released_middle": 88.0, + "pc_picked_top": 75.0, + "pc_nested_top": 69.0, + "pc_released_top": 68.0 + } + }, + "overall": { + "avg_sum_reward": 14.405273650527384, + "avg_max_reward": 7.158090181569347, + "pc_success": 65.0, + "n_episodes": 100, + "n_success": 65, + "pc_success_ci95": [ + 55.254443296887956, + 73.63575175690247 + ], + "eval_s": 1842.2228133678436, + "eval_ep_s": 18.42222813844681, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 92.0, + "pc_nested_middle": 88.0, + "pc_released_middle": 88.0, + "pc_picked_top": 75.0, + "pc_nested_top": 69.0, + "pc_released_top": 68.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..20a01f0593cbe2c86166771b2a7840af7e47c40f --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52a041534aef419745ffca6ef4c53cbab6173a7130a89d5a967f8e163c325d1 +size 522755 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a47735101781bc9f446920bc1fd3d878bf58237c --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760091e35d293c83fa728cd507217f2db6dbdcf1483a7cf14758f27826171f82 +size 601645 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b3e89bc125c88a1185783dbe8b2bbdacc4f60f61 --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17e24d5e2a5ef0a1cd29631bc183052a461b5507cd82f6e4d7d8061eecac597 +size 977672 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..70a6b50c0b5d92db0e2f474c6b6fb18b2cf8b8ae --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79527bebfa5db77222beac5e1ebbcacf4cd7b4f3a1d56d87e25aba7edb4997c9 +size 487291 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5c6d663651201688b73814c860d290e9f482c69d --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3725790de3edf97d0572d8eff0012ae27e6e0aeecc2a3f0ca10c13ead290dfc0 +size 488998 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..18d711d6e6138f7ee70eddb03066ea38d8a85f29 --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac24f097d6a51d86d85a65dfce3b6c89dcc10122a654ed858deb4209cf47bb37 +size 485974 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..19d9e2ce5c5e71670ba7df8f4651df5a20ede77a --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8aaa9343ad56af8259a0b460b74235f758e3da834cb46a325df5f2d4316a73 +size 1016137 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..05ff26bc65847789580bd54a78be2ed2dee08384 --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c51fa957e8b9d7ebc6ab062aa759a9613dc40dd8a8e9871701308b9739f49ec +size 433112 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ab4626bb441d2da2573ed42a6b024793d36f25d7 --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1e3f00164e36e288d5d911223fb31a08e33f68cc2c9ffc6cf14c1a987615e9 +size 420109 diff --git a/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8f91ff824499ce464f3fc449f98056a85a25ece8 --- /dev/null +++ b/eval/bsp10_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7910eb29022b238004d43c2f44ac1a06f183f14d83fe7c2cce31a669fa1dc257 +size 817312 diff --git a/eval/bsp10_L9_latency_s1000/eval_info.json b/eval/bsp10_L9_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..084f01f04a8a6e0605dad42ae968fbd052327462 --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663705, + 0.19046656255952266, + 19.999262549799724, + 0.15814316392313177, + 19.99936741098459, + 5.412563053227609, + 19.999105240321853, + 19.9993581228727, + 20.000851525118648, + 19.99934917398952, + 5.001695329442536, + 0.4587346895769807, + 20.00009781314237, + 0.3817447424930094, + 5.192663341013692, + 5.245383766138766, + 5.28407502895606, + 0.469375669180808, + 19.999513169904713, + 0.4645253613201249, + 5.216064011558306, + 19.99877961319592, + 19.99863067035327, + 5.290480628345673, + 5.380908955960935, + 19.999742702308364, + 19.999394325812084, + 0.3837684454705437, + 0.10542237017240752, + 20.000602761164483, + 0.40456452249054087, + 0.1593567705073412, + 5.140848935703619, + 0.48347041944694547, + 0.34100162617456564, + 19.998832411084962, + 0.18007169731728223, + 5.417513147892884, + 0.2670276673042341, + 19.99889878268503, + 19.99961399708814, + 19.999818826958354, + 0.2547543345044757, + 0.2589668670361651, + 5.437257960920908, + 19.998641850249406, + 19.99982147969666, + 0.18654146919027292, + 19.999962063823315, + 5.386432053459534, + 0.4464910720324533, + 5.450958372187133, + 5.345826576546776, + 0.32462669061105043, + 0.3107291387190193, + 19.998549221010474, + 0.4953566825877127, + 19.99954225991674, + 0.09889711725287931, + 5.401679799873072, + 5.284529913071696, + 5.17034438832364, + 19.999049471609773, + 19.999961565773685, + 19.999828397002844, + 5.128810228059169, + 5.386923734104572, + 19.999469560359888, + 19.999318113374706, + 19.999394204412507, + 0.2365888556963538, + 19.999936241414236, + 0.1882093697419438, + 5.346041405548142, + 0.285310007681538, + 19.999347404906835, + 20.00055107884635, + 20.000962778222632, + 19.999424750593892, + 0.15429615202350788, + 0.1346321055418036, + 20.000957991067814, + 0.3749037560625219, + 20.000220910650462, + 5.214925465697034, + 19.999214085579283, + 20.001531907364996, + 0.45326336868564976, + 20.00036379409621, + 0.47225815849407027, + 5.349920473130808, + 19.999130449988947, + 0.08694165881865246, + 19.9988192735477, + 20.00046864656114, + 0.07993237245264884, + 0.24115563482676527, + 0.16854701052639542, + 20.00087879449485, + 5.438347070988875 + ], + "max_rewards": [ + 10.0, + 0.055027076591106394, + 10.0, + 0.051609060870053014, + 10.0, + 1.535927638892138, + 10.0, + 10.0, + 10.0, + 10.0, + 4.526300588605985, + 1.2911331929313346, + 10.0, + 1.3619363043981578, + 1.5269071025618293, + 1.5484140310258248, + 1.5558190149069278, + 1.234653990052053, + 10.0, + 1.159091475859536, + 1.5571737564806403, + 10.0, + 10.0, + 1.5659913771183473, + 1.543797380922462, + 10.0, + 10.0, + 1.3323034079085385, + 0.03954587437443857, + 10.0, + 1.1117539768353, + 0.049893636929574714, + 1.576041018867873, + 1.4178791038991734, + 1.1917641760150288, + 10.0, + 1.2738320004176997, + 1.5576019562126435, + 1.3292839015249167, + 10.0, + 10.0, + 10.0, + 1.308406887169292, + 1.2570338860446069, + 1.5127003408583546, + 10.0, + 10.0, + 0.056959585995359774, + 10.0, + 1.5427430044582926, + 1.1918998265817913, + 1.546767450858214, + 1.5101260731503896, + 0.04910463411059185, + 0.04013640831453158, + 10.0, + 1.2142164374221889, + 10.0, + 0.047147270443475, + 1.56142301023197, + 1.5515912335723996, + 2.5582636689960125, + 10.0, + 10.0, + 10.0, + 1.543600974941345, + 1.5280777643198176, + 10.0, + 10.0, + 10.0, + 0.046064703206904256, + 10.0, + 0.038861941094689656, + 1.6344876838126376, + 1.3157366623367681, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3829077097076476, + 1.3684396869368318, + 10.0, + 1.2404560437037513, + 10.0, + 1.5654020688733858, + 10.0, + 10.0, + 1.177398186531489, + 10.0, + 1.1054883863872655, + 1.5596584615965594, + 10.0, + 1.231813613188872, + 10.0, + 10.0, + 0.06842551618263681, + 0.06639936142054803, + 0.06293488230441191, + 10.0, + 1.5462886280543713 + ], + "successes": [ + true, + false, + true, + false, + true, + false, + true, + true, + true, + true, + false, + false, + true, + false, + false, + false, + false, + false, + true, + false, + false, + true, + true, + false, + false, + true, + true, + false, + false, + true, + false, + false, + false, + false, + false, + true, + false, + false, + false, + true, + true, + true, + false, + false, + false, + true, + true, + false, + true, + false, + false, + false, + false, + false, + false, + true, + false, + true, + false, + false, + false, + false, + true, + true, + true, + false, + false, + true, + true, + true, + false, + true, + false, + false, + false, + true, + true, + true, + true, + false, + false, + true, + false, + true, + false, + true, + true, + false, + true, + false, + false, + true, + false, + true, + true, + false, + false, + false, + true, + false + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + } + ], + "pc_picked_middle": 70.0, + "pc_nested_middle": 66.0, + "pc_released_middle": 66.0, + "pc_picked_top": 49.0, + "pc_nested_top": 43.0, + "pc_released_top": 43.0 + }, + "n_episodes": 100, + "n_success": 43, + "pc_success": 43.0, + "pc_success_ci95": [ + 33.733298524110104, + 52.784610450787675 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 9.916105762995885, + "avg_max_reward": 4.9682464303700895, + "pc_success": 43.0, + "n_episodes": 100, + "n_success": 43, + "pc_success_ci95": [ + 33.733298524110104, + 52.784610450787675 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 70.0, + "pc_nested_middle": 66.0, + "pc_released_middle": 66.0, + "pc_picked_top": 49.0, + "pc_nested_top": 43.0, + "pc_released_top": 43.0 + } + }, + "overall": { + "avg_sum_reward": 9.916105762995885, + "avg_max_reward": 4.9682464303700895, + "pc_success": 43.0, + "n_episodes": 100, + "n_success": 43, + "pc_success_ci95": [ + 33.733298524110104, + 52.784610450787675 + ], + "eval_s": 2137.220871925354, + "eval_ep_s": 21.372208728790284, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 70.0, + "pc_nested_middle": 66.0, + "pc_released_middle": 66.0, + "pc_picked_top": 49.0, + "pc_nested_top": 43.0, + "pc_released_top": 43.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ed40755aec63ed536bfedbe18196b900cbf7523c --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35cf926da6ede7c574573125cd175e6740458d78c11dcd4b316455ad0c213a30 +size 499565 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..477236840d541a08637d544a66691e983674dd32 --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e895ca6e19547932214ffa1de226d7f687e89b222dfd4c43ff3a87bb908c4044 +size 816015 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b8287292a57a57daff0fab9b2a66d6679a3994d9 --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d2cbb491b4ba0fffc2fb8cb0b092d2f1f99a4c99d251a2fa6d254c77b0c027 +size 484153 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f9a9c80287f45f6e3e62abda5dd538184315327f --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bdd227222e69e447d2479fcfa3bd0d1d6db1727056d0bf98be3168559c4fa10 +size 814831 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e282568e9a138e6627c38d0b184bd4eecdbb901d --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac15002cfaf0e09fdc37dd81f108cf682fb54e5e324d38fcfc6188ad97fa21a +size 511697 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..60755d6ad8040015c003ad43523e0e8a7136634d --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d3cdbc60d5aeecf406a28b68119a9acfb11d7424f98c73d7d84eefd7bbcfa7f +size 918051 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ca604a3051673d4d3055787ec0560d005214676d --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee493e3ed9ac2a4bfb0368270ee68b546fba246c9a4269ee5b771a77f00bb5e +size 444872 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..307e79ed8b333a975896752af26259a9d11941d9 --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:462b039ab0eaa3b86d81e1773181ac294cc88eb869634e15f2687af0a80416d7 +size 439881 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..98fbcbd4ddd49e37c76ebecbcd58edc7efffa78e --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085ed4b6ed1f6899fccd467b14e6a60e185f9a92e8ad406827b1d5ed6b84be24 +size 421183 diff --git a/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..63a74fcfe4e95f08050fc814845fa74915f53f38 --- /dev/null +++ b/eval/bsp10_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344645675d562e9cce8b531f2a4a14e19ecd858a25b945c1c8e54fa62fe0312a +size 469487 diff --git a/eval/bsp10_L9_latency_s1001/eval_info.json b/eval/bsp10_L9_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ad8300156f0d8e53beca060cc19aeaee059180e1 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.3973724359301505, + 5.264505475271454, + 19.999260996146585, + 19.99918614363644, + 0.291621039701248, + 5.336692187875184, + 19.999107853380654, + 0.3331431893294282, + 9.999123076288663, + 19.999348746311796, + 19.999426256268666, + 0.2315727432994018, + 20.000115740860544, + 20.00040095747229, + 5.195748490657017, + 19.999028725314275, + 19.99965711031966, + 19.99884853631997, + 0.46205035886563683, + 19.999456955006792, + 19.999928113045353, + 0.2964223190030244, + 19.998687684038252, + 19.9991508299993, + 19.99966584115611, + 19.999740379745464, + 19.999372214497168, + 0.2637252767189312, + 0.06615515390922855, + 20.000569483896825, + 19.998863378091784, + 19.999479026914354, + 19.99901829127201, + 5.433797876591057, + 5.399597663270866, + 19.998829600391442, + 0.05133556391023353, + 20.0003111724996, + 0.34388037995378395, + 19.998840782108385, + 5.4646860352667845, + 19.99980352859547, + 19.99991190857492, + 0.26724461530694577, + 19.999812133853936, + 19.998655204228818, + 0.045764316295054064, + 0.07078002713210274, + 19.99997269787943, + 0.12337684067669263, + 5.4427372482936365, + 5.4007115288415655, + 19.99933113877666, + 0.445852997263647, + 20.000898702175927, + 19.998548499114214, + 0.23692781366425164, + 19.999488075257158, + 5.459299489175213, + 20.000113645071256, + 19.99968008086237, + 0.3472190151891533, + 0.08345383858298183, + 19.9999783529626, + 0.41424257439467926, + 19.998959361523642, + 9.999279681370748, + 0.049140318476763034, + 19.999355200791058, + 5.168729229495671, + 0.06755967689110409, + 19.999955819778876, + 0.1562813105083054, + 5.4851546504764315, + 20.000315115756457, + 19.99934740964826, + 20.00068519081653, + 20.00095960385881, + 5.0822640080379875, + 0.06121619971340775, + 0.046336306758880785, + 5.457268338274677, + 0.2448025502012222, + 0.09544680073318368, + 5.220633330040634, + 0.10370699813038586, + 0.2374126874566551, + 0.24801592903165082, + 0.3863330923420426, + 19.999051309093943, + 19.999289432104753, + 5.393931753897215, + 0.10751175973910954, + 19.998803303960685, + 20.000524122776316, + 0.03884631802806027, + 0.6109184468069425, + 5.228178565280617, + 20.000862069967226, + 0.039019329684166104 + ], + "max_rewards": [ + 1.5051971212270403, + 1.5056469089923117, + 10.0, + 10.0, + 0.059979142796917295, + 1.5713244482744173, + 10.0, + 1.3339754128332486, + 4.6450641708045595, + 10.0, + 10.0, + 0.06211380857073978, + 10.0, + 10.0, + 1.5614910433351454, + 10.0, + 10.0, + 10.0, + 1.1533045832804625, + 10.0, + 10.0, + 0.04556425850286716, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.331636930798061, + 0.06283280558965199, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5623661554076902, + 1.5668469616571405, + 10.0, + 0.02494065510940635, + 10.0, + 1.327418569987866, + 10.0, + 1.5761903716433308, + 10.0, + 10.0, + 1.2429927007561314, + 10.0, + 10.0, + 1.2331579427638133, + 0.06470635176264206, + 10.0, + 1.562777835352425, + 1.5762494154310258, + 1.5244505137839357, + 10.0, + 0.039825411022594515, + 10.0, + 10.0, + 1.1990251420539288, + 10.0, + 1.5434045941130976, + 10.0, + 10.0, + 0.05431834233361821, + 1.3396429055082384, + 10.0, + 1.3903478268806544, + 10.0, + 4.4815910355049855, + 1.3609461381685435, + 10.0, + 1.516424157780583, + 0.02973381066931413, + 10.0, + 0.05596024853541626, + 1.5543999634329644, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5683576005312319, + 0.03069969366699088, + 1.367909471472056, + 1.538875981350079, + 0.04726387287708744, + 1.6369634488387428, + 1.5135368969698213, + 0.04019283053931211, + 1.3544212165565606, + 1.1755898265513656, + 0.0540082275315773, + 10.0, + 10.0, + 4.559271622259906, + 1.2684425434271578, + 10.0, + 10.0, + 0.049291952684501705, + 1.5263150706595316, + 1.6015154704461758, + 10.0, + 0.06902281002894262 + ], + "successes": [ + false, + false, + true, + true, + false, + false, + true, + false, + false, + true, + true, + false, + true, + true, + false, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + false, + true, + false, + true, + false, + true, + true, + false, + true, + true, + false, + false, + true, + false, + false, + false, + true, + false, + true, + true, + false, + true, + false, + true, + true, + false, + false, + true, + false, + true, + false, + false, + true, + false, + false, + true, + false, + false, + true, + true, + true, + true, + false, + false, + false, + false, + false, + false, + false, + false, + false, + false, + false, + true, + true, + false, + false, + true, + true, + false, + false, + false, + true, + false + ], + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + } + ], + "pc_picked_middle": 75.0, + "pc_nested_middle": 69.0, + "pc_released_middle": 67.0, + "pc_picked_top": 51.0, + "pc_nested_top": 50.0, + "pc_released_top": 50.0 + }, + "n_episodes": 100, + "n_success": 48, + "pc_success": 48.0, + "pc_success_ci95": [ + 38.464551758051904, + 57.683422234776025 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 10.776776235781567, + "avg_max_reward": 5.420675262210558, + "pc_success": 48.0, + "n_episodes": 100, + "n_success": 48, + "pc_success_ci95": [ + 38.464551758051904, + 57.683422234776025 + ], + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 75.0, + "pc_nested_middle": 69.0, + "pc_released_middle": 67.0, + "pc_picked_top": 51.0, + "pc_nested_top": 50.0, + "pc_released_top": 50.0 + } + }, + "overall": { + "avg_sum_reward": 10.776776235781567, + "avg_max_reward": 5.420675262210558, + "pc_success": 48.0, + "n_episodes": 100, + "n_success": 48, + "pc_success_ci95": [ + 38.464551758051904, + 57.683422234776025 + ], + "eval_s": 1900.0897574424744, + "eval_ep_s": 19.000897581577302, + "video_paths": [ + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_2/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 75.0, + "pc_nested_middle": 69.0, + "pc_released_middle": 67.0, + "pc_picked_top": 51.0, + "pc_nested_top": 50.0, + "pc_released_top": 50.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..050c2206c3163e62cc630e1a0e8d88898ca8e337 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:681281881baf598380022589803945d1981dca701c4b0c3c29a88de118ff86a7 +size 902775 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..912adeef7cb6b5708a6417ffee1de3e178c113cf --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b230f48b6d46c614b11e679d8011ae40417d19b9939ed4101ec065448b6874b4 +size 953858 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7c89e381494ea063bef29b62cb8a267b23271ff2 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe865267296e2d01ce88ee5b46d3f7a41fa683287e4d73c5e157b1e8a09801b +size 531799 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..eefc53d0ba4c45c21d8377a23fe1dbc4fff4a493 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe8195df4c9ae45a40492a9d01cdbc297976560ad5cc368f5fa6dcce7ccd30a +size 531271 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..468ad640a6aee2dad13a1362e522003c8caab29b --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:120aded04bdd0dcf50a2dd3b959ad3752473a090939e47ea5da36e08f8e3f5d4 +size 1076273 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..68f4754558c30efb96febd6effabf29230fd5ea3 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:940575e85c953d1f03c3e7f5375e04860269df97dc374bd5adf4c3263040d354 +size 941907 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..67c82e6884531e886094f4d8bda2cf627f01767f --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:953c4aee889a31a76530bbba3b415b3f2d218758790953ef25ba89ab4da290cc +size 456810 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..aa0bcd7ba6627d215243f84762cf67b9127aa8f4 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8479d4af11460892317b4f51cab8bed38bb0328b7569aff766949b249c9cc098 +size 1018970 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..763ba306cff539990270dcf2ac5eebf1f1beee69 --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185a48dbebecc9397927708dace2c77aa759eb74e0b34396fc6a9f0646bd5141 +size 673718 diff --git a/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0e2c803aa852ecddc3d842cec341c76f93d59b6c --- /dev/null +++ b/eval/bsp10_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d852523a62c87649b96d4567e7e72e4e40c07eb4b07c300426e5d22b5ca0d9f +size 463621 diff --git a/eval/bsp10_L9_latency_s1002/eval_info.json b/eval/bsp10_L9_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6b6ae1eb68d474b334f2a8d9400064eed2ce63ec --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.459852075570206, + 0.14014078144569864, + 19.999260996737323, + 19.99918614267901, + 19.99924909378046, + 19.999301464402926, + 19.999109343159603, + 19.999385141625517, + 0.47914660501492135, + 19.999349630575708, + 19.999449548519898, + 5.420896102878585, + 5.4434449931778826, + 0.4518984060701805, + 5.436303793663257, + 19.999047418344574, + 19.999684240657412, + 19.998870127051923, + 19.99950554714855, + 0.38120000606070203, + 19.999914907723586, + 5.370864585483642, + 19.998619177250298, + 0.576054803512794, + 0.18754245484276832, + 5.345993141424817, + 19.99937516255445, + 0.4242851340492635, + 0.04072553342653762, + 5.469822454182906, + 5.226093588317432, + 19.999481498448233, + 19.9990188215162, + 19.99996840728746, + 5.421525989561444, + 5.326991646090403, + 5.480030043284458, + 5.471535994329937, + 20.000769470284574, + 19.998820699109, + 19.99958784825754, + 19.999804519519962, + 0.03747982057954191, + 0.4715243178792763, + 5.409461552518087, + 19.998648544984654, + 19.999796829564957, + 19.99983986153016, + 19.99842793257527, + 19.999825137845818, + 0.39562146516597074, + 0.050113724703600315, + 19.99933114392816, + 9.99884846026577, + 5.499516789633684, + 0.2534562527499937, + 19.998889507231, + 0.14029360244966704, + 5.486575365445374, + 5.5204995426958074, + 0.09608819824204029, + 5.303651283425414, + 0.09077992571507387, + 19.99999912101032, + 19.99976277146875, + 19.99897863233923, + 20.000242829489647, + 5.2213985924043405, + 5.188746729727063, + 0.12356256799345333, + 0.11959480662879673, + 20.000026170464885, + 0.08402690969451354, + 0.3668457432364125, + 0.4901229783490795, + 5.44366342540119, + 0.449606070249978, + 20.000910611325644, + 19.99942430429761, + 19.99977186999029, + 9.999062375139317, + 5.501491992808447, + 19.998599182692896, + 0.27308522785347744, + 0.10618243086455914, + 5.247239497795255, + 0.3056679392096957, + 19.999571406629205, + 0.4846951171009565, + 19.999047568804944, + 5.2514713277220695, + 19.99913910335799, + 19.99990102126255, + 19.998818023532856, + 20.000443856735753, + 0.04966652046558451, + 19.99935160697513, + 0.10226379282051745, + 5.430942602905667, + 0.065875429488505 + ], + "max_rewards": [ + 1.535744864628962, + 0.03820382904214248, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.0535432758912594, + 10.0, + 10.0, + 1.5424142159056313, + 1.582966720169786, + 1.4278590451356235, + 1.5957748211319804, + 10.0, + 10.0, + 10.0, + 10.0, + 1.1391011624235254, + 10.0, + 1.5441939475384778, + 10.0, + 1.1212421052836388, + 1.241617031348914, + 1.604320885137849, + 10.0, + 1.3211523831464584, + 0.026008019539197402, + 1.5431112150968822, + 1.5858443043324537, + 10.0, + 10.0, + 10.0, + 4.661943835650585, + 1.5546359480449454, + 1.507852118527122, + 1.5889902171290338, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5440310652716935, + 1.2395697458511004, + 1.5488930274028991, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2128561255748538, + 1.2600540511214504, + 10.0, + 1.581605669527741, + 1.562284102611495, + 1.5917735822307901, + 10.0, + 1.3574231067325448, + 1.492209615997792, + 1.5793469263208384, + 1.2523403080433955, + 1.532875041681128, + 1.357131498336725, + 10.0, + 10.0, + 10.0, + 10.0, + 1.552517357861583, + 1.5629468463889469, + 0.034059400905602555, + 0.03363743689716958, + 10.0, + 0.047906786670296464, + 1.3034580009461263, + 1.36107481993345, + 1.522922350545306, + 1.3692855921259144, + 10.0, + 10.0, + 10.0, + 1.6971498510962348, + 4.650372260767243, + 10.0, + 1.271614353501426, + 1.3418273749348653, + 1.5235942638311335, + 1.3593648356591135, + 10.0, + 1.298927103736306, + 10.0, + 1.5616669378796038, + 10.0, + 10.0, + 10.0, + 10.0, + 0.043961263637781745, + 10.0, + 1.3602956795091043, + 1.5536297427566839, + 1.291119050703935 + ], + "successes": [ + false, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + false, + false, + false, + true, + true, + true, + true, + false, + true, + false, + true, + false, + false, + false, + true, + false, + false, + false, + false, + true, + true, + true, + false, + false, + false, + false, + true, + true, + true, + true, + false, + false, + false, + true, + true, + true, + true, + true, + false, + false, + true, + false, + false, + false, + true, + false, + false, + false, + false, + false, + false, + true, + true, + true, + true, + false, + false, + false, + false, + true, + false, + false, + false, + false, + false, + true, + true, + true, + false, + false, + true, + false, + false, + false, + false, + true, + false, + true, + false, + true, + true, + true, + true, + false, + true, + false, + false, + false + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + } + ], + "pc_picked_middle": 80.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 72.0, + "pc_picked_top": 52.0, + "pc_nested_top": 47.0, + "pc_released_top": 47.0 + }, + "n_episodes": 100, + "n_success": 45, + "pc_success": 45.0, + "pc_success_ci95": [ + 35.61453797951198, + 54.75539700255786 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 10.565889767563881, + "avg_max_reward": 5.260702451220968, + "pc_success": 45.0, + "n_episodes": 100, + "n_success": 45, + "pc_success_ci95": [ + 35.61453797951198, + 54.75539700255786 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 80.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 72.0, + "pc_picked_top": 52.0, + "pc_nested_top": 47.0, + "pc_released_top": 47.0 + } + }, + "overall": { + "avg_sum_reward": 10.565889767563881, + "avg_max_reward": 5.260702451220968, + "pc_success": 45.0, + "n_episodes": 100, + "n_success": 45, + "pc_success_ci95": [ + 35.61453797951198, + 54.75539700255786 + ], + "eval_s": 1740.8541150093079, + "eval_ep_s": 17.40854115486145, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 80.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 72.0, + "pc_picked_top": 52.0, + "pc_nested_top": 47.0, + "pc_released_top": 47.0 + } +} \ No newline at end of file diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..775571faa8c4abe8ef593f27a16de26fee517cbb --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5efa8e5426ebaf3bc91bae96efa3e456dca9cce2d4a5b949696bc83a6e19741a +size 898486 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..90a5c95a9358c3acab8d8878741f2e26727c89df --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f9799390eff58bc5b899790ccecb5be27141e30c4374ff4deae0785bb4a353 +size 814544 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1b5d42a8c0210073be8c68a6adec2942778b9b32 --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0b7ca8e2050b4e9b0720f7f0b23e2846551f59891602911f19d03c0ede028e +size 502452 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cbbe7ca91f21028f83b4bd8bcce1cb52ec05368c --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935cd24857bb051b1d9d145fd3fb32cc3e983bdf31ba7c8d6f0f97ba6fa4752c +size 520334 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..27d7b89d2b45851629234ab0da227c4f3d20810f --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428d8cd413fac3414613630a0fa1c01933cb1050a7e2ed43516486e141c67779 +size 538461 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c46583052115e128179d5c0307070518847a6378 --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d4bd87802c3170cf005ea4e2461b2996d488147cc05ed71610aeb7b622b826 +size 530656 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..90cd37d40c875db5157110209680ecd3c5c387aa --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4fa974d504b9364b32ecc4d9446fddd5bed8b3b5af86ccae60312eb9e40287 +size 445501 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4a5c8967810fc1623d231552701d4aa8c7cbb011 --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69430c84b1f0090f78b5175cf2bdbf9f7d7f63ec25801ae6af3095b70b83e21 +size 829009 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..84e569045eb5657e1b0a8ae2d95c26cfcb7bd31b --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ede4ad19265dd2fc246bbca14d235961b65476c89f89881e4ea4972b6672adc +size 1034394 diff --git a/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5de6bef54f9a19e5b3f8141f7ca18bdcba68a34f --- /dev/null +++ b/eval/bsp10_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e623cd06da9f089756a10ad1d0c03c9906c9dda66e69d37db2a4b7521266fe6 +size 477014 diff --git a/eval/onestep_L0_latency_s1000/eval_info.json b/eval/onestep_L0_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1e2d80555cb3f300e5dcca27e944cf998b9844c6 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.0019989613347695, + 19.999376372577125, + 5.021962790216741, + 19.999186150284295, + 19.99928777761383, + 5.218571895165365, + 19.999092428850673, + 19.999455120812605, + 20.001108877385406, + 5.166788694926735, + 19.999433485656198, + 8.99841463384688, + 20.00016520740749, + 20.000464430868867, + 19.999411509402755, + 19.9989952094227, + 19.99969888963928, + 5.582299919640401, + 5.4790989018045835, + 5.259446880884502, + 20.000018083643063, + 5.5986701319739085, + 5.476583400595247, + 0.49643632741469446, + 5.003298485142197, + 0.6660559130780801, + 19.999375360996805, + 19.99989625120724, + 0.008062188936489356, + 20.000703883102517, + 19.998862510285264, + 0.01728013772254955, + 5.485856668949633, + 20.00010015904243, + 20.000380168751285, + 19.998805282119147, + 19.99977806304655, + 20.000472327655256, + 20.000787370884947, + 19.998889071241834, + 19.999652416789353, + 0.5099796118569109, + 20.000012454753122, + 20.00082465652619, + 5.559378140109815, + 19.99860994928406, + 19.999793927498697, + 19.99983446559511, + 20.00009208753415, + 19.999978613392052, + 19.99976068914755, + 0.4616814066518199, + 5.00181791847541, + 19.99957707048012, + 20.00106932944612, + 5.466399541119361, + 19.99884616250194, + 5.61938339068214, + 19.99961625868896, + 20.000087151359207, + 5.001848137971135, + 5.021292515305592, + 19.99905732351834, + 19.99997525014478, + 19.999836449363364, + 5.477409064437031, + 20.000314772657482, + 0.5249881373829436, + 19.99936337364214, + 19.999382216092002, + 0.44646496687906434, + 0.5307550590839032, + 7.388344585763762, + 19.9998238164723, + 20.000474436813427, + 19.999347409648262, + 20.00083439460439, + 20.001067823670688, + 19.99942491635393, + 0.4700728249908207, + 0.4537334158257831, + 20.001033356141207, + 19.998598502311367, + 20.000269520429846, + 0.01588027383714752, + 0.44429496486896114, + 20.0014991777512, + 5.47143783929885, + 20.000372945979414, + 0.5282206849144547, + 0.5244379164397819, + 5.652546121802896, + 5.001817153581268, + 5.009666794872103, + 20.00063193261739, + 19.999651850434166, + 19.99932675767156, + 0.4630086319850203, + 20.000882412719726, + 0.46708634287938067 + ], + "max_rewards": [ + 1.5547979723396335, + 10.0, + 1.5651049737495808, + 10.0, + 10.0, + 2.5822963661539085, + 10.0, + 10.0, + 10.0, + 1.5835527538302308, + 10.0, + 1.582960739180594, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5595264382944773, + 1.5880462508814728, + 1.575665976900367, + 10.0, + 1.553987591469228, + 1.5862973366312176, + 0.027706757453605402, + 1.613672098681181, + 0.02644702653174369, + 10.0, + 10.0, + 1.2800316844611563, + 10.0, + 10.0, + 1.368853909315773, + 1.5114064175091038, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.028771488916750965, + 10.0, + 10.0, + 1.5677711689141447, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.026035377641693724, + 1.5816279867880383, + 10.0, + 10.0, + 1.565528869136618, + 10.0, + 1.4886386055449083, + 10.0, + 10.0, + 1.5590208164644328, + 1.5536789975266645, + 10.0, + 10.0, + 10.0, + 1.5792592288842688, + 10.0, + 0.03415569893983139, + 10.0, + 10.0, + 0.027330264953582817, + 0.029401650230359455, + 1.5212625449480428, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.028400901226821262, + 0.026551518774884153, + 10.0, + 10.0, + 10.0, + 1.2891306847991713, + 0.03296110575156741, + 10.0, + 1.5607889045967125, + 10.0, + 0.031256949123677935, + 0.0313229559571242, + 1.5692585471389404, + 1.6256036924187556, + 1.5813699566347208, + 10.0, + 10.0, + 10.0, + 0.025361285827327107, + 10.0, + 0.02589011324040147 + ], + "successes": [ + false, + true, + false, + true, + true, + false, + true, + true, + true, + false, + true, + false, + true, + true, + true, + true, + true, + false, + false, + false, + true, + false, + false, + false, + false, + false, + true, + true, + false, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + false, + true, + false, + true, + true, + false, + false, + true, + true, + true, + false, + true, + false, + true, + true, + false, + false, + false, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + false, + false, + true, + false, + true, + false, + false, + false, + false, + false, + true, + true, + true, + false, + true, + false + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + } + ], + "pc_picked_middle": 86.0, + "pc_nested_middle": 83.0, + "pc_released_middle": 83.0, + "pc_picked_top": 62.0, + "pc_nested_top": 60.0, + "pc_released_top": 59.0 + }, + "n_episodes": 100, + "n_success": 59, + "pc_success": 59.0, + "pc_success_ci95": [ + 49.201430053410775, + 68.13268697886348 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 13.199854392365792, + "avg_max_reward": 6.329507336077627, + "pc_success": 59.0, + "n_episodes": 100, + "n_success": 59, + "pc_success_ci95": [ + 49.201430053410775, + 68.13268697886348 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 86.0, + "pc_nested_middle": 83.0, + "pc_released_middle": 83.0, + "pc_picked_top": 62.0, + "pc_nested_top": 60.0, + "pc_released_top": 59.0 + } + }, + "overall": { + "avg_sum_reward": 13.199854392365792, + "avg_max_reward": 6.329507336077627, + "pc_success": 59.0, + "n_episodes": 100, + "n_success": 59, + "pc_success_ci95": [ + 49.201430053410775, + 68.13268697886348 + ], + "eval_s": 3915.347553253174, + "eval_ep_s": 39.15347553730011, + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 86.0, + "pc_nested_middle": 83.0, + "pc_released_middle": 83.0, + "pc_picked_top": 62.0, + "pc_nested_top": 60.0, + "pc_released_top": 59.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..364376b03a4227a5001c38a4c1f9037270c6f39d --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55abed6e4e2b7623b647b89e9f48a6173749ee9406144688f73d3bc3b2224326 +size 435881 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cfffad8689814a7553249218661d00cb65fc6706 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4102707dd0e05b6a0aabe5321b543aac3e5599a686e281117263b2043ce42c6 +size 602049 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c7dd1ceb700c6025fcd8ba524a6043d25e39b19f --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e672977b82b71960b7e5b42ba8ce580e5f7c9a318305587b9c50966d8b590f +size 494246 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fe1610f08dd21dafb385541fac57be6567aef0d5 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e410c5a35ee6ca06ebe39d83e1eb3ad007d223e8461ca0879098c6bddccba121 +size 482021 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9ef6046e48d49f19f737fdb500ae6e2eb466af69 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394bba7369886ef0532c3db009620aaef3d5acfe9e2386e5dd58d002ec7f6679 +size 544517 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7e8ec284a6b8814a92ed88ad2c5e17a670293c01 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcee7133e0f51f15e18c49f4fcf50966a2038a8f6fb479eea98c43f3adeadaac +size 624850 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d18e0ad3a9565777f74536c3ab994d9b72d5109d --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50be5a7a4a8594c7a608d6a19b6eade795772a512a2d5957dd7b21dfe3939360 +size 468781 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7b3df6dd246e9ebbffb008485e1ae656b4bab9e2 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df30247f773c92b6e6742fa27f39785b42b9e0d71b735addad5e5201d2fd0f67 +size 427046 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ae3cab00fe9a132720d807f8cc413b83cb4beec3 --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e165d3c3b80b282d989da929aa2d1fd8a9652eb3e967f2193a3b751725615af3 +size 421212 diff --git a/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d10c7c8d52c2176e167b96e284706d8d7367d5da --- /dev/null +++ b/eval/onestep_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecba5dba6708abcfd4b7052df8bef3959b4773a44fca97acdee508d21b301f1a +size 618531 diff --git a/eval/onestep_L0_latency_s1001/eval_info.json b/eval/onestep_L0_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ef99d2ae13b6523fa5755ada64418045541b76a8 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 19.99935374632523, + 5.0218980931853, + 19.99918614686537, + 5.656657033167913, + 19.99925042729447, + 19.99909761675081, + 19.999445164853284, + 20.00106458800962, + 5.530348705056127, + 19.999400832945273, + 19.998563373435736, + 20.000191379794686, + 20.00047356362086, + 19.999410113918206, + 19.998813395962753, + 19.999708621234188, + 19.998883733179916, + 19.999527567473926, + 19.999456975116473, + 20.000015143845687, + 19.998779613009336, + 19.99863369521398, + 5.016325470191864, + 19.99966583956307, + 19.999786013710384, + 19.99937538860395, + 19.999809417753944, + 0.5738688274794993, + 20.000671752793732, + 19.99880680999196, + 19.99946452227457, + 19.999016834123815, + 19.99998623960076, + 20.00041977246903, + 19.99880618027438, + 5.580717427410482, + 20.000408208473594, + 20.000725945281737, + 5.456260614744835, + 19.999620030855173, + 19.999823474805005, + 19.99996795083383, + 20.000850726999417, + 19.999782270973437, + 19.99842078638443, + 19.99979394638952, + 19.99980751806678, + 20.000041246009264, + 19.999904297978034, + 19.99974956317616, + 19.99906400772118, + 19.999331121183623, + 5.592020802550541, + 20.001028235765396, + 19.998528364758005, + 5.4626671073407085, + 19.999488342026417, + 19.999594337466934, + 20.000149320491808, + 19.99968003841225, + 5.527054213900452, + 19.999053346244597, + 20.00004015565655, + 19.99980578405501, + 19.998963952965486, + 20.000232523032945, + 19.999449396115736, + 5.068080001800224, + 19.999379554809487, + 19.999548050357685, + 19.999922289236856, + 19.999329602609034, + 19.99983065262777, + 20.00036227592173, + 19.99934740964826, + 20.00086031040007, + 20.001021453262034, + 5.179810903662039, + 19.999727158730032, + 0.5039798656549486, + 20.000949767327057, + 19.998614803274606, + 20.000278110000007, + 0.09473680983951072, + 19.99920958709053, + 20.00154500140564, + 19.99958107424258, + 20.00038285069092, + 19.999046070415112, + 5.006858383198383, + 0.12728950633164438, + 19.99990102306699, + 19.998800606463597, + 20.00055844591426, + 19.99957653040077, + 19.999340797937997, + 19.999356284947545, + 20.000903371829523, + 19.999464316805188 + ], + "max_rewards": [ + 10.0, + 10.0, + 1.5737872410023654, + 10.0, + 1.574693658416827, + 10.0, + 10.0, + 10.0, + 10.0, + 1.538192641198463, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5590680260513519, + 10.0, + 10.0, + 10.0, + 10.0, + 0.028650434758637378, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5495169094310954, + 10.0, + 10.0, + 1.5781307134313463, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.574151745861116, + 10.0, + 10.0, + 1.521508204951477, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5405566179179258, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5761643240262917, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.592992187012816, + 10.0, + 0.024938521621290177, + 10.0, + 10.0, + 10.0, + 1.309802187018497, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5219517945896968, + 1.1240662492182776, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + false, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 98.0, + "pc_nested_middle": 96.0, + "pc_released_middle": 96.0, + "pc_picked_top": 84.0, + "pc_nested_top": 84.0, + "pc_released_top": 84.0 + }, + "n_episodes": 100, + "n_success": 84, + "pc_success": 84.0, + "pc_success_ci95": [ + 75.57973061072975, + 89.90471151119522 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 17.45373522264725, + "avg_max_reward": 8.611881714565074, + "pc_success": 84.0, + "n_episodes": 100, + "n_success": 84, + "pc_success_ci95": [ + 75.57973061072975, + 89.90471151119522 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 96.0, + "pc_released_middle": 96.0, + "pc_picked_top": 84.0, + "pc_nested_top": 84.0, + "pc_released_top": 84.0 + } + }, + "overall": { + "avg_sum_reward": 17.45373522264725, + "avg_max_reward": 8.611881714565074, + "pc_success": 84.0, + "n_episodes": 100, + "n_success": 84, + "pc_success_ci95": [ + 75.57973061072975, + 89.90471151119522 + ], + "eval_s": 2863.1063492298126, + "eval_ep_s": 28.6310634970665, + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 96.0, + "pc_released_middle": 96.0, + "pc_picked_top": 84.0, + "pc_nested_top": 84.0, + "pc_released_top": 84.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9176aa03cb40c84d0ebca077d6ee76c2e243149d --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874913dc6ed69f346c68abf9c12cb3dd251ffe1935cbedbbfedc756e73805d23 +size 492383 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..59c426c20e6ef2fa35af4f878651ded2d543fb6c --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8ec25ae76f6bb44cf1bf9ccbcce22d3f17f43ee694c7364d56145bdfd29b63 +size 426962 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..486045cf32c13810d2e777e16d845317fbe58e38 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9adc0628342bce206f764639ed50fc355608ebbddf43fe2ab99a8fd73977f677 +size 592704 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..785a2dc55f998adcf12269143a4ab31686271ec1 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4b7acade27a9e9b727d972e3d9d221487a64d0aeb75e7f4ad5d12921976259 +size 479693 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..eef7182e92cdc4a50dcd71ea0e3898796e830718 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e2ee14962760f830c22e6f72fb8aa221fb717de1d90035e0fe7bf7606182d2 +size 568945 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0174d367a94a9fde787c96195526981b3081bcd0 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98bc79c0973c9ce47bde4ebc35bbdb5fdc18abfada45dad000de4affc7e9731 +size 460097 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e35f9861a04754c995ffa8689e02cbbad8aa4353 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baa749853973103df0a824f95db018ed820c9cf8511c758dc8a372bde226eb7a +size 461248 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..84535d453863d89e24de76e8ad719f42a54c358f --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd84565630b70ba6259c7024e3bcc8749880e4b664893463f3a9b7423c8ed49 +size 462140 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0e7cf4cc1fdabf185b6cdc29e1a0aaab40b21e1a --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f00a22a21d0237fb39a766ad8f7235212eca5cd6dc6713fab56e5e5824af1a +size 430383 diff --git a/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2252f909623d83f186a9c8a291a17eae3799eef6 --- /dev/null +++ b/eval/onestep_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb2f09bbdb90a921905f3f1707aa6a753224baf48b670a0a759bb980b5929bd0 +size 576610 diff --git a/eval/onestep_L0_latency_s1002/eval_info.json b/eval/onestep_L0_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..15959295cf704147a0d14843af46ab42e5f35d42 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 19.999375220805348, + 5.504105232865222, + 19.999186145684416, + 5.480906322314188, + 0.4879465715664876, + 19.999090926141136, + 5.4709361904671265, + 20.00112190895157, + 5.548193610901253, + 19.999407277178666, + 3.9984146338468793, + 20.000191108416566, + 20.000467735368524, + 5.014825934481952, + 19.999003232749992, + 19.999700076932537, + 5.488036970919932, + 5.485636464682404, + 5.4920886588860744, + 20.000016852718417, + 5.536110655182854, + 5.455396101336876, + 19.999150829999294, + 19.999665839034755, + 5.472934614411104, + 0.46915094050265704, + 19.999846764273713, + 5.0009077575946765, + 20.000808412552708, + 5.47778811499416, + 19.999472469429026, + 5.478506922833857, + 0.3773746705781187, + 20.000396047839146, + 19.99881673863429, + 19.999828346190935, + 20.000446789028004, + 20.0007375320498, + 19.9984816471248, + 19.998731376802333, + 19.999820485513954, + 19.999942564686496, + 20.000848645580493, + 19.999716790677777, + 5.479873652399428, + 0.46299836268879646, + 19.99984097328579, + 20.000089996939753, + 19.99989450957592, + 19.999704982545193, + 19.999064004422543, + 19.999331146474088, + 19.998848460265766, + 20.00092864596246, + 19.998543733075497, + 19.998319826312354, + 19.999475490883356, + 19.999598058791495, + 20.000107073581333, + 5.001841671775112, + 5.501414528320215, + 19.999046263996654, + 20.0000338239417, + 19.99982779333962, + 5.468449316694124, + 20.000315892813205, + 19.999450293466886, + 19.99929009041838, + 19.999373855957312, + 19.99948898352716, + 19.999881119145922, + 0.46475936515988137, + 19.999828967661095, + 20.000342942876593, + 9.999146506158695, + 20.000892552782997, + 20.001068001014378, + 5.466367151606301, + 0.46356093044649005, + 0.4728295334305266, + 20.00102889220981, + 19.998598273981205, + 20.000265580724893, + 19.999090753856947, + 19.999220129585336, + 20.00155680024011, + 19.999556833534264, + 20.000366089956877, + 5.020989733606498, + 19.999290032583378, + 5.538329399652918, + 19.999901021249862, + 5.472985296456168, + 20.000633791986715, + 19.999632705887876, + 19.99934558978292, + 19.99908330240632, + 20.000881788608048, + 19.999445465078278 + ], + "max_rewards": [ + 10.0, + 10.0, + 1.5429152285715761, + 10.0, + 1.573373576542693, + 0.028161184352756607, + 10.0, + 1.5752518232446173, + 10.0, + 1.5795739392075236, + 10.0, + 1.5764480437327588, + 10.0, + 10.0, + 4.596687269948661, + 10.0, + 10.0, + 1.5774004977111131, + 1.5785533540934007, + 1.5470182940828408, + 10.0, + 1.5693793326812022, + 1.585478600326109, + 10.0, + 10.0, + 1.5755837223962117, + 0.02628201409595987, + 10.0, + 1.5427543043100034, + 10.0, + 1.5840212646756247, + 10.0, + 1.5411846816188153, + 1.364216850918707, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5935545861673008, + 0.027833655414254754, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5201202463643946, + 1.5584958325565608, + 10.0, + 10.0, + 10.0, + 1.5770592750934083, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.03270432223316444, + 10.0, + 10.0, + 1.572926256132765, + 10.0, + 10.0, + 1.5744260554850968, + 0.027950677262852275, + 0.030952817797799903, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5605822730437677, + 10.0, + 1.5818358991700823, + 10.0, + 1.5469099277706229, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + false, + true, + false, + false, + true, + false, + true, + false, + true, + false, + true, + true, + false, + true, + true, + false, + false, + false, + true, + false, + false, + true, + true, + false, + false, + true, + false, + true, + false, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + false, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 94.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 92.0, + "pc_picked_top": 71.0, + "pc_nested_top": 70.0, + "pc_released_top": 70.0 + }, + "n_episodes": 100, + "n_success": 69, + "pc_success": 69.0, + "pc_success_ci95": [ + 59.37394428051057, + 77.22030278762395 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 15.160373038535194, + "avg_max_reward": 7.321696358070025, + "pc_success": 69.0, + "n_episodes": 100, + "n_success": 69, + "pc_success_ci95": [ + 59.37394428051057, + 77.22030278762395 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 94.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 92.0, + "pc_picked_top": 71.0, + "pc_nested_top": 70.0, + "pc_released_top": 70.0 + } + }, + "overall": { + "avg_sum_reward": 15.160373038535194, + "avg_max_reward": 7.321696358070025, + "pc_success": 69.0, + "n_episodes": 100, + "n_success": 69, + "pc_success_ci95": [ + 59.37394428051057, + 77.22030278762395 + ], + "eval_s": 1862.2226498126984, + "eval_ep_s": 18.622226502895355, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 94.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 92.0, + "pc_picked_top": 71.0, + "pc_nested_top": 70.0, + "pc_released_top": 70.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..dc7c48aff510b206a4631abb9d8e7a5329805c10 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4edcce6c7a0f35d384c98b058f79f11432ab3e13fa26ba50a8ac3b261b83e0d +size 489902 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2fde04a01b776756925ec676666bb358d300ff59 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fe4853746c2085b7a11fb86569e8b1367fb327204b2f6c01521a6e07c90255e +size 436565 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..165a77586078b3c7ef5a47e8e35584b4c4fe5cd3 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3249864cfe390f588a643e91d71eb52f83ced820100bd9794317d10db33a15 +size 632032 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..83e55ea8eeee011d05a70f94dca55ded9857dff9 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ee2c21da3b1d6a381f6c447d596c349a4d5939801b12ccad13476c11179465 +size 496254 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c257f6b90c925fb3f68ba13a4a2f91a4a6bc25b5 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e0a6962da47587ea9d021867fe40648df8ae5197f2744acde989c272d76c6c6 +size 635078 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3ac7fdc5a8fa76cbf2bccd2a0f0e15eaf72b6628 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3f3dc75e2a22c0e6b4306a4f7957147fd7b3dcdc043f1721aaaca98d124c0f +size 293082 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b19780be317fb6c021bd34ba51bd3014010cbaf7 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ab59720833d3d9aa7259f7dee35a77d465b897fd4726c4513b029b23908812 +size 456437 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..58c6374da5ee449aaba43f9bc95d7b66948635ee --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab67fb9086bdcd3cb8b42e04932534c5f7f6cdf385955759954f750125c6d680 +size 680285 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bbbf5ea64399290b951d5a3e58f822bd4e649b4d --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a0fdc345ceb359a534116df9e5153dc82458382fe308824cc7b1168cd4a7b3 +size 401136 diff --git a/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5624ccd0b49ccb8655f599187f268470c3c9f383 --- /dev/null +++ b/eval/onestep_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691003c9cb5a2fbf6d875b8b255207864dc782b0dee78f4aab0a2874e35c2d04 +size 561202 diff --git a/eval/onestep_L0_none_s1000/eval_info.json b/eval/onestep_L0_none_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6b3b649c9764caad6cebcb726dfdc2235390b4ff --- /dev/null +++ b/eval/onestep_L0_none_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.002412707504995, + 0.5537114345816077, + 5.018529776998724, + 5.005285813918668, + 5.741069977434699, + 0.5034732501569485, + 19.99909711172424, + 7.240952792369779, + 20.001145811951048, + 1.6218283343425142, + 5.002106822687439, + 5.539037361414216, + 20.00011535632767, + 20.0004628018799, + 19.999408185513893, + 19.999978593180263, + 5.451716346123496, + 3.998702880590324, + 5.67141088581987, + 5.014657064282395, + 20.000093859727414, + 5.660484799103044, + 5.455624714903665, + 0.08333469563948126, + 5.003108234212313, + 5.592787550808537, + 19.99937544509277, + 5.391948444557036, + 0.015226832262183243, + 5.558693070138448, + 5.4765422084436395, + 0.031282013835765565, + 5.613858060205767, + 5.492102780076797, + 5.120894368485631, + 19.998826419179107, + 5.754058297052836, + 20.00056295469885, + 20.000896291341768, + 19.99895524265062, + 19.999853303687956, + 0.5346397026303215, + 20.00000444128413, + 20.000824146537205, + 19.999811396051534, + 0.025362699448413406, + 0.47644598374324976, + 20.001135924644203, + 20.00013767248884, + 0.6018583223517631, + 19.99975612012068, + 0.5761305943642976, + 5.001827492767756, + 5.011823238397141, + 0.06778820431945654, + 5.453904415006714, + 0.14268897538606395, + 20.00019538881753, + 0.597042294754047, + 20.000074472403593, + 5.001596518061266, + 5.020392277211647, + 19.999046668110083, + 19.999873558745417, + 9.998649317652735, + 5.611621909144895, + 20.000332219482118, + 0.5535602706394875, + 19.99930966355653, + 0.4785068557764689, + 0.4634348991646593, + 19.999940507932042, + 0.5922077290942975, + 19.999827407406386, + 20.000477604958423, + 6.533329778190643, + 20.000675936229534, + 20.001008526889862, + 5.213993925857172, + 0.5006364584577998, + 0.5235283076647403, + 20.00068686713134, + 5.497628507393023, + 20.000244202732095, + 5.000856047401417, + 0.4946241445852583, + 20.001544670354633, + 5.456023974384678, + 0.05906260490056692, + 0.23517403004725213, + 0.17023464961390067, + 1.565100638584307, + 0.26319501452232985, + 5.009335766945483, + 20.00064835708505, + 0.4621124503843712, + 5.002022372836917, + 0.5658673709004103, + 0.03570551135683975, + 0.6226887599071764 + ], + "max_rewards": [ + 1.5719503181123027, + 0.028485884690351737, + 1.59856702638639, + 1.561467752504195, + 1.5838090502673179, + 0.03455820091120454, + 10.0, + 1.5817444714920839, + 10.0, + 1.1858050405185236, + 1.5368223051450074, + 1.600422991030877, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5898958081192844, + 1.5723312528300335, + 1.5764435149666345, + 1.5564336007031465, + 10.0, + 1.6083865921615201, + 1.5733656889095686, + 0.028231036754518213, + 4.6717785888993015, + 1.5803760143686478, + 10.0, + 1.5658345060890748, + 0.0387128660961088, + 1.57382332337767, + 1.5908070969052437, + 0.03845861082366964, + 1.577775123552411, + 1.5672567494295855, + 1.5734513372155674, + 10.0, + 1.5476937581985462, + 10.0, + 10.0, + 10.0, + 10.0, + 0.03060575363091611, + 10.0, + 10.0, + 10.0, + 0.03152599882882068, + 0.027874112638951898, + 10.0, + 10.0, + 0.03014541011699634, + 10.0, + 0.03163619544845975, + 1.6280700782329447, + 1.5702194983856677, + 0.028985601198729616, + 1.5622962282528472, + 0.02831437311075724, + 10.0, + 0.029534045334891124, + 10.0, + 1.5948685598151355, + 1.5598828850332738, + 10.0, + 10.0, + 1.6553918647448742, + 1.5768202771364237, + 10.0, + 0.03073349313622198, + 10.0, + 0.026878028144268873, + 0.029172403451346307, + 10.0, + 0.028663694690137742, + 10.0, + 10.0, + 1.6051724287435685, + 10.0, + 10.0, + 1.5778776835310186, + 0.03333258431169317, + 0.035927698194657354, + 10.0, + 1.5734371827841107, + 10.0, + 1.572297637692972, + 0.03090842283216888, + 10.0, + 1.576150082844023, + 0.02678488606546081, + 0.03267023235473532, + 1.1363358028043962, + 1.1309131466066291, + 0.02618071862200111, + 1.5716704073851648, + 10.0, + 0.030529584596667547, + 1.5641825559342704, + 0.027598933645795243, + 0.03141875635135727, + 0.029022925068941663 + ], + "successes": [ + false, + false, + false, + false, + false, + false, + true, + false, + true, + false, + false, + false, + true, + true, + true, + true, + false, + false, + false, + false, + true, + false, + false, + false, + false, + false, + true, + false, + false, + false, + false, + false, + false, + false, + false, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + false, + false, + true, + true, + false, + true, + false, + false, + false, + false, + false, + false, + true, + false, + true, + false, + false, + true, + true, + false, + false, + true, + false, + true, + false, + false, + true, + false, + true, + true, + false, + true, + true, + false, + false, + false, + true, + false, + true, + false, + false, + true, + false, + false, + false, + false, + false, + false, + false, + true, + false, + false, + false, + false, + false + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + } + ], + "pc_picked_middle": 73.0, + "pc_nested_middle": 70.0, + "pc_released_middle": 69.0, + "pc_picked_top": 37.0, + "pc_nested_top": 35.0, + "pc_released_top": 35.0 + }, + "n_episodes": 100, + "n_success": 34, + "pc_success": 34.0, + "pc_success_ci95": [ + 25.461520797348165, + 43.72227114527538 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 8.910397706617164, + "avg_max_reward": 4.0422871868216, + "pc_success": 34.0, + "n_episodes": 100, + "n_success": 34, + "pc_success_ci95": [ + 25.461520797348165, + 43.72227114527538 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 73.0, + "pc_nested_middle": 70.0, + "pc_released_middle": 69.0, + "pc_picked_top": 37.0, + "pc_nested_top": 35.0, + "pc_released_top": 35.0 + } + }, + "overall": { + "avg_sum_reward": 8.910397706617164, + "avg_max_reward": 4.0422871868216, + "pc_success": 34.0, + "n_episodes": 100, + "n_success": 34, + "pc_success_ci95": [ + 25.461520797348165, + 43.72227114527538 + ], + "eval_s": 1952.4536073207855, + "eval_ep_s": 19.524536077976226, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 73.0, + "pc_nested_middle": 70.0, + "pc_released_middle": 69.0, + "pc_picked_top": 37.0, + "pc_nested_top": 35.0, + "pc_released_top": 35.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..27d60e4d3911376777b70afc37240e7b18a23627 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a34d2bf8d56e0da2ad79bf3f3483da560b7de750ff241017ae83c0a8fdd7ed18 +size 720561 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ac8144e46ab05ff950d2e63a97ec94aa20972b96 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092d47d6887d4de54fb604397380776daf874c41e10a19a265c5e8f2caab52f0 +size 341944 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..65b0870d2e0144882384a39e00e4278435fca7fe --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ca8a4e665da3c70d64ef5d73c0c076b88f000f1be7f823099007b53318093c +size 596983 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..22a2e29894ae1311cf4ece61531f5a540a510ce2 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b27b3591210d847b75c7f205f2dfbc3393e1482716b1cd895288990e42282c +size 569609 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4b5c717a5710578279ab96f8b0fe1b222f929328 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24b73344aec7d50742c31f070aca4b826f001fa99024c7f2e0b80699acbc292 +size 657737 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..80ffd8fc7d63369948737bf472791e8d1955ac87 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db604ab3a042e1fca2efb52821eee6e7534d6f91e9a455956c90033577cc17c +size 418276 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1bd061360378ecde758ce35503af399f4c3a5bda --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f14db89f339aecce9b6cca16d989814bf0e1fb5476f304efe9deffa026c4f7 +size 457744 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0d0e6a4b774fb8abdd9ccfafb75977a407583df3 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e833a3a609b9bf5ccd955f685e5ffc9f9e25d28cf5506f7b4cb90018639208c1 +size 803625 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a110254e28065288acbafdad2821912c79cdee63 --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8dd65b01ba38347f468361bd920d8a829a663e937bd51623c0437156fe8e877 +size 388173 diff --git a/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2588012534f829b7f501246f188c33abc7f9b66b --- /dev/null +++ b/eval/onestep_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6904703b009318bb5b2b07915467e8b1d448cdf2a6c47e5f6deca58c4a2e7a9 +size 642275 diff --git a/eval/onestep_L0_none_s1001/eval_info.json b/eval/onestep_L0_none_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f33b050fcdb8c613a05140387c2e71ecc4084a10 --- /dev/null +++ b/eval/onestep_L0_none_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.002278531198707, + 0.4672550291362072, + 5.024698074216133, + 0.1846021174263317, + 5.739185231546827, + 0.5616995067252528, + 19.99908635921275, + 5.5613552396532855, + 0.49636132931073296, + 5.584128469013839, + 19.999371886309174, + 5.543009989832263, + 20.00006499565685, + 20.00042833232082, + 20.00065901177436, + 7.421256305855012, + 0.5823712575154083, + 5.623854004344562, + 5.527340690710698, + 19.999456975116477, + 5.424607091944575, + 0.5374127069947119, + 19.99861936235102, + 5.016411459243403, + 19.999665839034755, + 5.508676327328828, + 5.0015234472144385, + 5.42737196023299, + 0.7173400586952197, + 20.00062743462258, + 5.022280463769436, + 0.6855335527923021, + 0.551291604596766, + 6.719314962636005, + 5.587791086506366, + 19.998806223654533, + 19.999861375588306, + 5.480236251600022, + 20.000737718286587, + 5.503328767839575, + 0.5629856344564442, + 19.999825438033294, + 5.053000981932627, + 20.000634956866143, + 0.45365980818790685, + 5.02432644984731, + 19.99979394638952, + 0.2596516859701574, + 5.570773637090481, + 2.5173919216283895, + 6.787897772960468, + 0.6106827475750323, + 6.524944957386956, + 5.019824832015267, + 20.000974401224358, + 0.5953011835325874, + 5.019716730855895, + 19.999474452701918, + 19.999607847767013, + 20.0001669004183, + 0.24662209575880323, + 5.663432686841254, + 5.260197811222541, + 0.3462671647623058, + 19.99982826481321, + 5.2543515008835975, + 20.001108446919503, + 0.5282947267013115, + 5.551061208147269, + 20.000147114066323, + 0.5329424903511437, + 5.22161903420599, + 0.531615989193332, + 0.4019846584809259, + 20.00045941717503, + 7.404966631050838, + 20.00088703936021, + 0.5092375626326533, + 5.231861919631994, + 0.5712568585740835, + 0.488633924395395, + 5.433755266615218, + 19.998598357844088, + 0.5492238972977131, + 0.6723412643763715, + 19.999208036220534, + 0.5874944691470924, + 5.533836215546648, + 20.0001024748743, + 5.022768140132699, + 19.99929003258338, + 19.999134967921517, + 0.12513331031777564, + 5.506018501239296, + 5.533748628029093, + 19.999667541324946, + 5.419749108153498, + 0.5086197305855944, + 20.00095034920198, + 19.999465696380675 + ], + "max_rewards": [ + 1.6062459451119795, + 0.027173923812530143, + 1.5989577431669257, + 0.02359857111714747, + 1.5685613857966954, + 0.03109128387928861, + 10.0, + 1.584091025317682, + 0.0380574004024552, + 1.5737157612288568, + 10.0, + 1.580068333969865, + 10.0, + 10.0, + 10.0, + 1.570730274843493, + 0.029530338902145292, + 1.5706539117122502, + 1.5555494602837492, + 10.0, + 1.575821442244445, + 0.02617840536395366, + 10.0, + 1.58285777810516, + 10.0, + 1.560516054360496, + 1.5622236030220595, + 1.5926890268069995, + 0.03471746475168891, + 10.0, + 1.5798564486148998, + 0.033798267118244296, + 0.03193945084126226, + 1.5910902888487604, + 1.5759167097355626, + 10.0, + 10.0, + 1.5796951749770853, + 10.0, + 1.5722647757241917, + 0.0294333896721638, + 10.0, + 1.5725332915000476, + 10.0, + 0.0276536934586884, + 1.5684420954082459, + 10.0, + 0.0267241304405772, + 1.575296343167376, + 1.439080839088481, + 1.5640081724050345, + 0.027390661607452405, + 1.5289953791380992, + 1.557027978277391, + 10.0, + 0.02684962610173458, + 1.5872703723601311, + 10.0, + 10.0, + 10.0, + 0.024489433445415765, + 1.5636309012376803, + 1.5692406334517335, + 0.028385939666688897, + 10.0, + 1.5671799465488931, + 10.0, + 0.030349788852613524, + 1.5710430776429123, + 10.0, + 0.027225418175555793, + 1.5607625264854303, + 0.02731809454990486, + 0.03121187872447906, + 10.0, + 1.584420254033882, + 10.0, + 0.03413056420474003, + 1.5686431715859537, + 0.031529353027601514, + 0.029602515924375905, + 1.5600265521551093, + 10.0, + 0.029838790288776007, + 0.03167313603265243, + 10.0, + 0.02964996312949708, + 1.562292023403022, + 10.0, + 1.6098140948683284, + 10.0, + 10.0, + 0.025413439663801163, + 1.5752228620620286, + 1.5782729963658033, + 10.0, + 1.5452888990093652, + 0.027379536048787956, + 10.0, + 10.0 + ], + "successes": [ + false, + false, + false, + false, + false, + false, + true, + false, + false, + false, + true, + false, + true, + true, + true, + false, + false, + false, + false, + true, + false, + false, + true, + false, + true, + false, + false, + false, + false, + true, + false, + false, + false, + false, + false, + true, + true, + false, + true, + false, + false, + true, + false, + true, + false, + false, + true, + false, + false, + false, + false, + false, + false, + false, + true, + false, + false, + true, + true, + true, + false, + false, + false, + false, + true, + false, + true, + false, + false, + true, + false, + false, + false, + false, + true, + false, + true, + false, + false, + false, + false, + false, + true, + false, + false, + true, + false, + false, + true, + false, + true, + true, + false, + false, + false, + true, + false, + false, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 72.0, + "pc_nested_middle": 71.0, + "pc_released_middle": 71.0, + "pc_picked_top": 37.0, + "pc_nested_top": 32.0, + "pc_released_top": 32.0 + }, + "n_episodes": 100, + "n_success": 32, + "pc_success": 32.0, + "pc_success_ci95": [ + 23.669147324999095, + 41.662618610452384 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 8.731364198516083, + "avg_max_reward": 3.836123320132703, + "pc_success": 32.0, + "n_episodes": 100, + "n_success": 32, + "pc_success_ci95": [ + 23.669147324999095, + 41.662618610452384 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 72.0, + "pc_nested_middle": 71.0, + "pc_released_middle": 71.0, + "pc_picked_top": 37.0, + "pc_nested_top": 32.0, + "pc_released_top": 32.0 + } + }, + "overall": { + "avg_sum_reward": 8.731364198516083, + "avg_max_reward": 3.836123320132703, + "pc_success": 32.0, + "n_episodes": 100, + "n_success": 32, + "pc_success_ci95": [ + 23.669147324999095, + 41.662618610452384 + ], + "eval_s": 1955.3437309265137, + "eval_ep_s": 19.553437321186067, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 72.0, + "pc_nested_middle": 71.0, + "pc_released_middle": 71.0, + "pc_picked_top": 37.0, + "pc_nested_top": 32.0, + "pc_released_top": 32.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1ae868a7861099e64ef1ed635f388d1d8418d13a --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b4a1553aad084598ed950f5b2eb40053ffd206c8ab5fe57285787b2e291bb9f +size 793955 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b14d6c84b87a8e9ab7af1d7caf09de386ddcb6b8 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544fbbdc70c2ff52bb357bcf560a642901f265efcde0d4f0fe49a1e741098aeb +size 374074 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..aba1600d17162e91cac45f98cc582e460a26bcd2 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9319aa0dea2e5f70d366a60737a40974b0d6e0d43847fa8b9a4f39994da960 +size 857547 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c833fccd96205ce0828eb27e5b982c37d2563ffd --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1445d1733f1baa0a6f970abeb7a597044168d771f4109a3e2e3108054a66c9f7 +size 475108 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b4679d0608a23c7bb2c7904e07f58090103e9e3d --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b102a63acbd2bd18006ff2b27dd0c295991b73b23a8b900fcd444d9704b2b7fe +size 547791 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6204c0bacc5ce29d0cdd18d50ef369af4de98e97 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3e94059d02cf40cb3e966a06e4227bc60c2ceb45b18ae39afad455805aa878 +size 304480 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..79f5ba292c20521e8f09147318f8a3efcd90e9f0 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6c37ecbb2d6a1c5e468cc37d360b46b1b268a78bed37c80b3246283d529433 +size 514876 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a1e1b4445e4e6687a7115ef51275d3439990acb4 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00507febee7118a3845368e5e774be02a5e19ca69d6bc16a2b68c9209e0d0471 +size 726773 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3534e32178143d28946edf1c7b67d72cee11d113 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011dc5c7b9be2437d0cdeed03c16ef870242318e3cee1287392afa31bb4d29f3 +size 657503 diff --git a/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1c1cf2bba69a63768b8b05ba6ac66caa7a56e149 --- /dev/null +++ b/eval/onestep_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33323304cd8a354149839aba5166e16cbfeff2bff02e9631b479d81769e7f450 +size 630392 diff --git a/eval/onestep_L0_none_s1002/eval_info.json b/eval/onestep_L0_none_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..8c493d6f9c040ddeb7e2bc448da4d97e6a0d9ca0 --- /dev/null +++ b/eval/onestep_L0_none_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 5.001803776038721, + 0.4556653251607301, + 0.568899911359732, + 20.00007044106082, + 5.214105602852888, + 0.478677396701096, + 19.99908742022369, + 5.558463270329781, + 20.001107078005834, + 5.60416361280707, + 19.99942181054663, + 5.0092551487875525, + 5.106573522635503, + 20.000423403939404, + 5.624931132529322, + 0.5757458644675232, + 19.999798051654444, + 5.5701557136015545, + 5.529617588762022, + 5.018358672542119, + 20.000094765540982, + 5.474292493751337, + 5.475582155051437, + 5.01485730329268, + 19.999665842418892, + 0.5464166495260073, + 19.99937718503884, + 0.5703066747611755, + 20.000176573615363, + 6.774380574426235, + 5.030263580231537, + 5.002996293485634, + 5.485334839536155, + 0.5122634455056209, + 20.00028571106707, + 0.2750959813531504, + 19.999800369928757, + 5.559574571544421, + 0.5674092434441341, + 5.483296911940785, + 0.48673781774244385, + 19.999819171140008, + 5.19017735487713, + 0.5826302782165318, + 5.401422656007721, + 5.508270183040829, + 19.999798722534983, + 19.99985375580463, + 20.00013405025795, + 0.47084170584249074, + 19.99969745587929, + 7.3495185965580205, + 19.99933114647409, + 5.018237000896905, + 20.000956916845375, + 5.459348019942565, + 5.503069472259148, + 5.00586803603536, + 19.999597900354132, + 5.353565752195728, + 0.2495350258574981, + 5.02299570243898, + 5.279654370665715, + 6.807639389815293, + 5.611623477669489, + 0.2605978206672116, + 5.011648835291933, + 0.5944660931166738, + 0.554504973600302, + 19.999383582242462, + 19.999514772663932, + 19.999718286936265, + 0.46721605100568264, + 6.789088478875285, + 20.000093102104806, + 19.99934740964826, + 20.000860702018837, + 20.000623824967715, + 5.0021528076000745, + 0.4743850209077386, + 0.5112747005007027, + 5.490869630493458, + 5.474698950226043, + 5.195485604313463, + 5.000714835163571, + 0.4699795784039559, + 20.001561956001677, + 5.461775272022248, + 20.00038011324321, + 5.0192283817784755, + 19.99929003258338, + 0.5261110410051744, + 5.579452764460307, + 5.005844721303062, + 20.000620180279306, + 1.918947561921092, + 5.197938476637912, + 19.999983246494622, + 20.000906703594517, + 19.999457217217365 + ], + "max_rewards": [ + 1.5497264001107993, + 0.03055181285532571, + 0.03232081819602106, + 10.0, + 1.575532269916272, + 0.03519052514059251, + 10.0, + 1.5344581513395474, + 10.0, + 1.5573236493903313, + 10.0, + 1.5611480657293062, + 1.5774621679341534, + 10.0, + 1.560178032450302, + 0.03152572831247347, + 10.0, + 1.5885729187015745, + 1.5718728004694236, + 1.5610377037239083, + 10.0, + 1.5738901936112204, + 1.56998705695835, + 1.5889876512836185, + 10.0, + 0.030464492662355402, + 10.0, + 0.03604508681453222, + 10.0, + 1.558937479455294, + 1.585491377293334, + 1.55907794584042, + 1.5695066904121133, + 0.03080638869383845, + 10.0, + 0.02511715569634665, + 10.0, + 1.5746832822300492, + 0.03098187225875315, + 1.5710326219036705, + 0.03128706884105281, + 10.0, + 1.7162732978323878, + 0.029913053087693653, + 1.5761218661145302, + 1.5886360019037031, + 10.0, + 10.0, + 10.0, + 0.03520316757999209, + 10.0, + 1.5688897812386497, + 10.0, + 1.5849141695825661, + 10.0, + 1.5647268954140856, + 1.5848666041067367, + 1.5811425915079511, + 10.0, + 1.5781021267809392, + 0.025891077163243903, + 1.5634576604108048, + 1.5728742133520859, + 1.5892795278837273, + 1.588264219837466, + 0.02613197747511231, + 1.5284923348510042, + 0.02705369578945438, + 0.03611376439731806, + 10.0, + 10.0, + 10.0, + 0.042183766576819104, + 1.5817661257237647, + 10.0, + 10.0, + 10.0, + 10.0, + 1.584276193398387, + 0.031084385973992545, + 0.03973415666327618, + 1.5638866850225535, + 1.5757287964257447, + 1.5969094035014584, + 1.5671327327231501, + 0.030120341594018774, + 10.0, + 1.5718364473482236, + 10.0, + 1.5758505338968638, + 10.0, + 0.032341227302557285, + 1.5643403148737796, + 1.56287332196254, + 10.0, + 1.4065816484047398, + 1.5422279808527293, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + false, + false, + false, + true, + false, + false, + true, + false, + true, + false, + true, + false, + false, + true, + false, + false, + true, + false, + false, + false, + true, + false, + false, + false, + true, + false, + true, + false, + true, + false, + false, + false, + false, + false, + true, + false, + true, + false, + false, + false, + false, + true, + false, + false, + false, + false, + true, + true, + true, + false, + true, + false, + true, + false, + true, + false, + false, + false, + true, + false, + false, + false, + false, + false, + false, + false, + false, + false, + false, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + false, + false, + false, + false, + false, + false, + true, + false, + true, + false, + true, + false, + false, + false, + true, + false, + false, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 79.0, + "pc_nested_middle": 78.0, + "pc_released_middle": 78.0, + "pc_picked_top": 37.0, + "pc_nested_top": 34.0, + "pc_released_top": 34.0 + }, + "n_episodes": 100, + "n_success": 34, + "pc_success": 34.0, + "pc_success_ci95": [ + 25.461520797348165, + 43.72227114527538 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 9.313962425981096, + "avg_max_reward": 4.11338419496779, + "pc_success": 34.0, + "n_episodes": 100, + "n_success": 34, + "pc_success_ci95": [ + 25.461520797348165, + 43.72227114527538 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 79.0, + "pc_nested_middle": 78.0, + "pc_released_middle": 78.0, + "pc_picked_top": 37.0, + "pc_nested_top": 34.0, + "pc_released_top": 34.0 + } + }, + "overall": { + "avg_sum_reward": 9.313962425981096, + "avg_max_reward": 4.11338419496779, + "pc_success": 34.0, + "n_episodes": 100, + "n_success": 34, + "pc_success_ci95": [ + 25.461520797348165, + 43.72227114527538 + ], + "eval_s": 1911.427990913391, + "eval_ep_s": 19.114279913902283, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 79.0, + "pc_nested_middle": 78.0, + "pc_released_middle": 78.0, + "pc_picked_top": 37.0, + "pc_nested_top": 34.0, + "pc_released_top": 34.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2a93af0ac837b4f8a60902d6c909ee5ed1e7d4a8 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714bca084b22227482e62951d8bfd1900443e920b245ee44689a1fa575f98b91 +size 555508 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d51741fcc0407c603fea051c77a4079e60427354 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd9291e4315b9a68746f29c9494d04ae9870f2bc64c7ff316f4a3caee07f78e +size 323721 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f9bb6b2154f8a77059ca1747ac8039caf3813355 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb178bc3a83e2c6e3645004d6f33361a19f0e7df17e7b4834dc63285f727c1f +size 676271 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..717aaeae7583402a255de7b471261b94db5ffee7 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28adfb3a3432f9602d91f3c07e8f3418da7daee0aa555065655fafc350cc85a7 +size 621894 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a6a1d7a110bca7aa7776495373f9a08fd1bca799 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7333bca46d4efbffb87f7163db3ea2994e4d31f89e4b9fe5bedca26bf8069616 +size 763078 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..87b256ca9d16a918c3e7168d07563b3e1a86ba11 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f757feca428d4d4534229edf8c1fe03475674cbcef15a662d1b32f462b5af8ab +size 392403 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1cc8a14d490c829426155fd5a10b5cf0d717bed1 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0925382adc08b45e6990d52131a6804615498280d48edd554c345b1c6e914408 +size 466045 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b7b4acfe21405c9d5d2b83e1c750ba1204c7da42 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be45ae6b779c05ef573dd9431c352d9d58f87a6128cdedc7839ef268e1b0327 +size 752507 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5f85510f746b248b15d8eeddff87debae9450643 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3e93b453ad8c36afa459e408838baaae3356118f71713247d7b2322c0ce5a8 +size 423741 diff --git a/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..13de2ce53d462e47555c1aec07a0ed15b0e93829 --- /dev/null +++ b/eval/onestep_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a7001fe9e89f936030f84596f3d993087c2bd3dc7ec3734e15fa36b615daf7 +size 507303 diff --git a/eval/onestep_L6_latency_s1000/eval_info.json b/eval/onestep_L6_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7d82884fc4c8caeee5fe0519de2688bb94277ede --- /dev/null +++ b/eval/onestep_L6_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 5.0981248041234055, + 19.999260998111108, + 19.999186142679008, + 19.99920763638359, + 19.99927729227062, + 19.999103811813562, + 19.999412203454803, + 20.001023102193123, + 0.2646098254811933, + 5.011611996976347, + 19.998560689088862, + 20.00016745031583, + 5.21108840119831, + 0.0731051279231939, + 19.99900380136923, + 19.99969782648757, + 19.998837727406784, + 9.998961847955385, + 0.03450160878570885, + 19.999973487816114, + 19.998779614673815, + 19.99862406423602, + 19.9991507843242, + 0.06185554032275642, + 9.998917266235791, + 19.99937544509277, + 19.99982164792433, + 19.998924166880442, + 20.000625052754383, + 19.998828306649145, + 0.02399355978734219, + 0.3968733694427926, + 20.00006869248155, + 20.000272852630992, + 19.998829108662772, + 19.999841577643117, + 20.0003939780206, + 5.210365266460991, + 19.998879694147096, + 19.999615328517912, + 5.223270981960752, + 6.774128007398131, + 20.000765759184794, + 0.10492992857948946, + 19.998635011585886, + 19.999793946389524, + 0.05680478657812016, + 20.00004041632468, + 19.999795426600286, + 19.999696828661964, + 19.99906400215184, + 0.027957943521177087, + 19.99958774923977, + 0.1317078380674993, + 19.998538629415396, + 19.998832231457875, + 19.999463659868905, + 19.999597994515746, + 5.537130618039593, + 0.02381152424018429, + 19.999198494262306, + 19.99905765021956, + 5.151428948410945, + 19.999824377937482, + 19.998961449305646, + 0.04056364988732919, + 0.023200407432702908, + 19.99935202160734, + 19.9993740430805, + 5.243783163029439, + 20.00004669836467, + 19.999329603675793, + 0.142892660148488, + 0.07545158388239326, + 19.99934740481729, + 20.000663754802492, + 20.001030334790762, + 19.999424079631588, + 19.999809501929555, + 19.999484339324002, + 0.15197982213002492, + 19.998603124599597, + 20.000268895612244, + 5.009390695932561, + 0.0800417695057456, + 20.001531028042496, + 5.2532159422939255, + 20.00036450867765, + 0.0033670965704717393, + 19.999290032583378, + 19.999120997403036, + 0.012273653543465213, + 19.99880555929755, + 20.00059939549946, + 0.11698733062810374, + 0.12319762926393196, + 5.2554059473493115, + 5.34565161984996, + 19.999521141761434 + ], + "max_rewards": [ + 10.0, + 1.567443005732862, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.1785324435301723, + 1.5417233917596846, + 10.0, + 10.0, + 1.5751094354272883, + 1.3082606611812717, + 10.0, + 10.0, + 10.0, + 1.5602384475182838, + 1.1600155222631645, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2224784370571307, + 1.5805894511110523, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3511874931045296, + 1.2504510337908656, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5865701772334537, + 10.0, + 10.0, + 1.5071937234988522, + 1.561962351903495, + 10.0, + 1.2491534975604528, + 10.0, + 10.0, + 1.27293853198994, + 10.0, + 10.0, + 10.0, + 10.0, + 1.214198925359982, + 10.0, + 1.3197427485751836, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5723924336218866, + 1.2447926405202137, + 10.0, + 10.0, + 1.50036670690101, + 10.0, + 10.0, + 1.3681477133344493, + 1.3504979967500903, + 10.0, + 10.0, + 1.5594636804398032, + 10.0, + 10.0, + 0.02825737546365792, + 1.307444860757829, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2013499095996494, + 10.0, + 10.0, + 1.5649513314351369, + 1.2980458241205994, + 10.0, + 1.573142306409323, + 10.0, + 1.1308493537122624, + 10.0, + 10.0, + 1.2207642404153933, + 10.0, + 10.0, + 1.3719791553351264, + 1.2962517618190204, + 1.5363416012652102, + 1.573249235185318, + 10.0 + ], + "successes": [ + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + false, + false, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + false, + true, + true, + false, + false, + true, + false, + true, + true, + false, + true, + true, + true, + true, + false, + true, + false, + true, + true, + true, + true, + false, + false, + true, + true, + false, + true, + true, + false, + false, + true, + true, + false, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + false, + false, + true, + false, + true, + false, + true, + true, + false, + true, + true, + false, + false, + false, + false, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 89.0, + "pc_nested_middle": 79.0, + "pc_released_middle": 79.0, + "pc_picked_top": 71.0, + "pc_nested_top": 66.0, + "pc_released_top": 66.0 + }, + "n_episodes": 100, + "n_success": 64, + "pc_success": 64.0, + "pc_success_ci95": [ + 54.235402451608735, + 72.72877959859568 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 13.712638864772527, + "avg_max_reward": 6.887060774056838, + "pc_success": 64.0, + "n_episodes": 100, + "n_success": 64, + "pc_success_ci95": [ + 54.235402451608735, + 72.72877959859568 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 89.0, + "pc_nested_middle": 79.0, + "pc_released_middle": 79.0, + "pc_picked_top": 71.0, + "pc_nested_top": 66.0, + "pc_released_top": 66.0 + } + }, + "overall": { + "avg_sum_reward": 13.712638864772527, + "avg_max_reward": 6.887060774056838, + "pc_success": 64.0, + "n_episodes": 100, + "n_success": 64, + "pc_success_ci95": [ + 54.235402451608735, + 72.72877959859568 + ], + "eval_s": 1856.6246585845947, + "eval_ep_s": 18.566246592998503, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 89.0, + "pc_nested_middle": 79.0, + "pc_released_middle": 79.0, + "pc_picked_top": 71.0, + "pc_nested_top": 66.0, + "pc_released_top": 66.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4b8218d925917028715f8f140b294a7ccc85083a --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa2fe8c7974ca51547a74da5a4e48a1375bd1e114ded79cfac07a979d50f784 +size 486263 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d52560e17a4f8c9300a064e18a5a8d85c188b21d --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8b0a44ade5c65f847ac6942d220a7b2d19fa50b9374d19cb1f80a9d9484470 +size 941813 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d491457d4a4ee2c00472104607e86f0a1b57b472 --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea362524280fea53abd1adf6f7b0601df27b55ddae48e54a6085cf41dbbc9d4 +size 509790 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1449e60efb06ab06d7ea76e329e81675b3db8b2d --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe9552f699b3f5c512ee4f5d91264a5b8c938cd4a3402b5e1bb4b3cf7d04278 +size 481040 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7172c74c691097b1cfd708b2aa34d9fbc2ab1e34 --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f7d61feb19991089a6d2e1b0d75bd8056a2bf6ea21615497ab7e41dd619135 +size 466491 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3a2aab53cd0e5016731b794f9b78b36df72c5ff7 --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6192c24b69ae039e78e65c9bd251503a88572170ab932f21012417b43c6990 +size 483020 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..63e4192983aecee2b2c5d72174771a7453bf75a7 --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb37e1dc57c9162501a3d4196db2bfa60b854f64e0b46013f36e36fb9ea89f2e +size 462935 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1db453f65a5cbdee1c7a4eba2977fc91934942e8 --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b19016d50f7565b1b327153a8abf6e9c1bc3e40b34799b1d650794e117008a0 +size 427408 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..10a8d13e330df5427ec6489ed1efcf3067f4ca5e --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadd805f54474fabaa46ed7834790a3b949f98037fb95a619ce459b3bcadc316 +size 418960 diff --git a/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..da9ed072270db829a568cda38f63d289d54a3061 --- /dev/null +++ b/eval/onestep_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58b92e56227ba221eabc7816533798ae516bfaa6b54ae1b21b2b67e14e82b4b +size 968110 diff --git a/eval/onestep_L6_latency_s1001/eval_info.json b/eval/onestep_L6_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..13b5cdca9217059fe0e13dfaf878c62b39c24677 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974173766371, + 9.999209033300794, + 19.999260996855575, + 19.999186142679008, + 0.004128082632821495, + 19.999241274796226, + 19.99909476614765, + 19.999425133903856, + 20.001106677152467, + 19.99889181167748, + 19.999426532120523, + 19.998560338044452, + 0.13765071719821842, + 20.000463030171073, + 19.99941011561874, + 19.999055961487457, + 19.999686711236784, + 19.998858047273526, + 19.99949937659504, + 5.161933430620066, + 19.99995270319679, + 19.998779613009333, + 19.998628972394158, + 19.999150824053086, + 19.99921522030574, + 5.087596277769183, + 19.99937544509277, + 19.99982245011876, + 9.998804131560929, + 0.1383153979677132, + 19.998807871517865, + 0.03279950545850674, + 19.999003719013178, + 19.99995928902129, + 0.14559519073157545, + 5.046248178641571, + 19.999851581714, + 20.00040523766727, + 20.000729083836216, + 19.998902656949937, + 19.999639202074416, + 19.99982163745051, + 19.999951500809694, + 19.998815236187532, + 20.000176106043327, + 5.021114757614951, + 19.999793823505232, + 19.999839272857088, + 20.000029976700326, + 19.99981963798233, + 5.496622938546267, + 19.999063970318918, + 19.999331146474088, + 19.999569940784664, + 20.00098821263718, + 19.998507798344537, + 19.998827692582932, + 8.999261489342583, + 19.99960655747511, + 20.000123559353046, + 19.99968302220348, + 19.999198647858694, + 5.35731371667942, + 19.999992235963607, + 9.998649317652735, + 19.99896137141953, + 20.000346885315498, + 19.999446173049023, + 5.082273048458783, + 19.99938394321171, + 19.99951610878272, + 19.999006843595147, + 19.999329601004852, + 19.999836113132456, + 20.000455356146983, + 19.99934735504953, + 20.00072579905437, + 20.000952562510214, + 19.99942491635393, + 0.023172729328056696, + 0.045428047443784925, + 5.141326848316947, + 19.99859888751328, + 9.99884781857064, + 0.07218046748603091, + 19.999082143516688, + 20.00154256266527, + 19.999573869295958, + 20.000363134260702, + 19.99904609492362, + 0.023154215195796413, + 19.999125145365266, + 0.5534980864446166, + 19.99879848615054, + 20.000541392184296, + 5.372549544342377, + 19.999343881891726, + 19.999306117128324, + 20.000905240080165, + 19.999463506642112 + ], + "max_rewards": [ + 10.0, + 1.6452596072940602, + 10.0, + 10.0, + 1.1224223309580923, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3457743404973128, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5767913536671228, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.551421045392218, + 10.0, + 10.0, + 1.597519906885534, + 1.3549481829974432, + 10.0, + 1.3492186207415786, + 10.0, + 10.0, + 1.1858685156416844, + 1.5676713978343884, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5335868571781517, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5726910507981526, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5777029340715456, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5580031353704298, + 10.0, + 1.5537570792633428, + 10.0, + 10.0, + 10.0, + 1.58378973527204, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3188831734574658, + 1.3827508831046775, + 1.5205333095059743, + 10.0, + 1.6254572789792774, + 1.317954069623929, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.034248894901712346, + 10.0, + 1.2499728188787458, + 10.0, + 10.0, + 1.509287280306086, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + true, + false, + false, + true, + false, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + false, + true, + false, + false, + true, + true, + true, + true, + true, + false, + true, + false, + true, + true, + false, + true, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 91.0, + "pc_nested_middle": 90.0, + "pc_released_middle": 90.0, + "pc_picked_top": 85.0, + "pc_nested_top": 81.0, + "pc_released_top": 80.0 + }, + "n_episodes": 100, + "n_success": 76, + "pc_success": 76.0, + "pc_success_ci95": [ + 66.76766365018553, + 83.30867444305122 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 16.169063689604688, + "avg_max_reward": 7.93635513802621, + "pc_success": 76.0, + "n_episodes": 100, + "n_success": 76, + "pc_success_ci95": [ + 66.76766365018553, + 83.30867444305122 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 91.0, + "pc_nested_middle": 90.0, + "pc_released_middle": 90.0, + "pc_picked_top": 85.0, + "pc_nested_top": 81.0, + "pc_released_top": 80.0 + } + }, + "overall": { + "avg_sum_reward": 16.169063689604688, + "avg_max_reward": 7.93635513802621, + "pc_success": 76.0, + "n_episodes": 100, + "n_success": 76, + "pc_success_ci95": [ + 66.76766365018553, + 83.30867444305122 + ], + "eval_s": 1653.0889718532562, + "eval_ep_s": 16.53088972568512, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 91.0, + "pc_nested_middle": 90.0, + "pc_released_middle": 90.0, + "pc_picked_top": 85.0, + "pc_nested_top": 81.0, + "pc_released_top": 80.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e239efb3a906d1c4f90e3c6c76a83a5f4171ce49 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fca47d7d6596184303a32863828ce78f2405c8fbd8172072a2563102be80657 +size 488067 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..940c030314ec6322cb12f79ff511d62b8cc346cf --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4a81144d86097ee5b08917128ae37284de9fc0fa41df5c7848006911782f72 +size 894134 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..99d7d293f11a7c55e6e0204d2889015fce4649c3 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1596136608dff0346d8390b77be90e792d8e939a5201dde9d8eec37e79eefc +size 506944 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fb6a4ccd24e6df7b6c48b58e3903cc95e50369cc --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd9fbd19a4d227131e4754ff304079bc1f03170d5fc9ec0f60097dd741c0971 +size 492814 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ff9f85c1d13a1b55c224111b2b3249fbf1ad217 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef61c3b5539bf0a9588a57be8b18bb4134eed51d542c6856271acc6dcb7d3ce2 +size 706641 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..73153ed4769334bb767d9ad9acf54e003d10ebaa --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1527acd388e547fe5c38aedc755626a0aa9174685ebefe53ede669a6e63e76b4 +size 490027 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ad2c59e9f489a2a2cf2e14f1727baa4452e224f --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e134a6f8f2f7befd5e9a06d17b2ec2498b0557790a317b084644d475f018f2d3 +size 465300 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..dd13af7fb52d947fbda62440c40c92131b91bc14 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0692ff975dd27867c7dd590c421071565e1f5da224960d1ecc94ce2eb8958961 +size 438630 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..388966f2507a04002fae5434968315ae708cc9c8 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c2ae05290593e8f52d06f2b3a5d9a94bc4692053537c58b84d0a28558d7b72 +size 445472 diff --git a/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..482570eed400b4c714bb24d434561e47b6e63e55 --- /dev/null +++ b/eval/onestep_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b6f1abe66d02b7e43086e10c8ae05b305b63ab5fb004f4edbcb4e84acec86e +size 627931 diff --git a/eval/onestep_L6_latency_s1002/eval_info.json b/eval/onestep_L6_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e299a98453ab8712b517da5e304bd497218ce7ae --- /dev/null +++ b/eval/onestep_L6_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 19.999378315431525, + 19.99926100174845, + 19.999191335072382, + 5.048245690975715, + 5.42300643362603, + 19.99910339072712, + 19.99936428170327, + 20.001015028033365, + 19.999354081203137, + 19.999511826318994, + 5.060519395349716, + 20.000169182230312, + 0.2427811223640045, + 0.032754985220663335, + 19.999009553439603, + 19.999693446645722, + 19.99885518283233, + 19.99952683596146, + 19.998809129351322, + 5.387211130134434, + 19.998779613009336, + 19.998625776618606, + 19.99915078298653, + 0.09725305104349224, + 19.999900371518294, + 19.99937544509277, + 19.999803856239367, + 9.998804131560929, + 20.000696429069393, + 19.99882921694129, + 19.999469984203312, + 0.029326358414214493, + 0.1886739803351476, + 20.00033445757002, + 0.16714293818040415, + 19.999814334267736, + 20.000385278189988, + 20.00069868497439, + 0.055076225895172026, + 19.999597366890157, + 19.999812391281225, + 19.999949757509892, + 20.00073205299376, + 9.999262958140827, + 19.998627209456817, + 9.999142178288173, + 0.4842922198905266, + 20.000022096637508, + 19.99983265243646, + 19.99970472037255, + 19.99906400772118, + 0.055304039418345385, + 5.561290786907724, + 20.000936529745438, + 0.12719168541726245, + 19.998878408419575, + 19.9994909281666, + 5.017854692568124, + 5.397480606064256, + 0.07398049860773404, + 0.05878776827397658, + 5.085260165041877, + 20.0000910056365, + 0.255124746352567, + 0.14569071038088033, + 5.018896205034979, + 9.998883216606224, + 19.999345407482473, + 19.999397481757903, + 19.999541418187622, + 5.068535027419319, + 19.999329602642053, + 19.999836502611593, + 5.473684632851045, + 19.99934740964826, + 20.000743273773566, + 20.000977679973552, + 0.1289727988201742, + 19.99978556738332, + 0.1538804515779023, + 20.000918780364298, + 5.015765276223773, + 20.00026328298784, + 9.99885672390546, + 19.999226044561958, + 20.001547788942073, + 19.99956894330645, + 5.195801921551369, + 19.999046083733965, + 5.015291756951465, + 19.999125721144708, + 0.03820380022200398, + 19.998801071294526, + 20.000534711003095, + 19.9996246916592, + 0.05275116970917204, + 19.999321934701797, + 20.00088859725077, + 19.99948482111411 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 1.5803453776644139, + 4.7686062416437345, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.564946598876341, + 10.0, + 1.3473747303248667, + 1.3109825996289568, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.562043312029246, + 10.0, + 10.0, + 10.0, + 1.2256757418599058, + 10.0, + 10.0, + 10.0, + 1.609429575907834, + 10.0, + 10.0, + 10.0, + 0.05214489807466227, + 1.374134604799139, + 10.0, + 1.1960825549396463, + 10.0, + 10.0, + 10.0, + 0.09950088024635462, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5637075768175097, + 10.0, + 1.5695006702563519, + 1.26475760669795, + 10.0, + 10.0, + 10.0, + 10.0, + 1.1992730350210512, + 1.5795402218386667, + 10.0, + 1.208929779994052, + 10.0, + 10.0, + 1.5147922639494167, + 1.568883140242571, + 1.236834927985387, + 1.1807765276104591, + 1.5160291445932934, + 10.0, + 1.3763759670874065, + 1.280789212378495, + 4.514621519501648, + 1.6021804061251217, + 10.0, + 10.0, + 10.0, + 1.5685891501351774, + 10.0, + 10.0, + 1.5734829177656466, + 10.0, + 10.0, + 10.0, + 1.155930317409898, + 10.0, + 1.373846395272138, + 10.0, + 1.5776048710321104, + 10.0, + 1.6006116887970598, + 10.0, + 10.0, + 10.0, + 1.5664727086863375, + 10.0, + 1.5706852432157559, + 10.0, + 1.225185676679123, + 10.0, + 10.0, + 10.0, + 1.274883918196479, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + false, + true, + false, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + true, + false, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + false, + true, + true, + false, + false, + false, + false, + false, + true, + false, + false, + false, + false, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + false, + true, + false, + true, + false, + true, + false, + true, + true, + true, + false, + true, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 89.0, + "pc_nested_middle": 82.0, + "pc_released_middle": 82.0, + "pc_picked_top": 68.0, + "pc_nested_top": 68.0, + "pc_released_top": 68.0 + }, + "n_episodes": 100, + "n_success": 63, + "pc_success": 63.0, + "pc_success_ci95": [ + 53.22052958094291, + 71.81763946567547 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 13.851322259811615, + "avg_max_reward": 6.863555520032841, + "pc_success": 63.0, + "n_episodes": 100, + "n_success": 63, + "pc_success_ci95": [ + 53.22052958094291, + 71.81763946567547 + ], + "video_paths": [ + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 89.0, + "pc_nested_middle": 82.0, + "pc_released_middle": 82.0, + "pc_picked_top": 68.0, + "pc_nested_top": 68.0, + "pc_released_top": 68.0 + } + }, + "overall": { + "avg_sum_reward": 13.851322259811615, + "avg_max_reward": 6.863555520032841, + "pc_success": 63.0, + "n_episodes": 100, + "n_success": 63, + "pc_success_ci95": [ + 53.22052958094291, + 71.81763946567547 + ], + "eval_s": 1962.1251134872437, + "eval_ep_s": 19.62125114440918, + "video_paths": [ + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_5/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 89.0, + "pc_nested_middle": 82.0, + "pc_released_middle": 82.0, + "pc_picked_top": 68.0, + "pc_nested_top": 68.0, + "pc_released_top": 68.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..40e09fc228c3a6c96221f92c686e316a5ea8f649 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d005e5159b0ca6f22d026c6753c84f7121498c4cc48384b37935ed55a9db9f +size 483962 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..df3d8e0b49aeaef3f4993e526a22d076d34959b3 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce31b194080ce135b891ed6b79a0668b93eb43f24c3c0b8763eca4e3200de07 +size 425529 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9786680c53d3c415dbb4d53a22ac85e09ecf9126 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ea6a5b1c27ec3df2e9307b682a40db93b06dfed9e495b3a2c52924b3a51c8b +size 503588 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..926a70143d110e48dabe52d9cfb378cc145db69c --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fa333e9cd55e2f5331c3ae345ea351e6e15609d1ec2419591f4b5d59237ac1 +size 472226 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d221e8ca4d77ef6c3b78f60ca3a3d02b42e4583f --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7476376d52a96b44947cf9ef2896c0c448a0c7b1db2708694a61e48fa3766c9 +size 1028430 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..58e4be8bf3fe5f0b32422f35f03b6516e01aadc4 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef42c6fbe07d285f442f88aab9a3b2349d7422da96a96bf544de24e8be9597b0 +size 1003067 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d8746a654c24abc5f7206425d4c32160b0d2e296 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a3434844a70556fab7b30ad133da00ae0296427262fe6adc12db12c4e53b23 +size 460928 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bcb5ca220d252530cc3b25bbcdd44e628612415f --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37afd5b27ec8179a0ce3a5695259485979c8d17c97d6bc50a902d724739e3f6e +size 737020 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f6593f22d9c7ca4a1e1700f04503403f6efc5065 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83d17012a6f3c40f37668cdd9e4ad08be8cff51d99945e73966d75d83f46e0a +size 417507 diff --git a/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c2ab7a6380f6feb7c70b6615e0f086f12481eab4 --- /dev/null +++ b/eval/onestep_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732c268f7750b87da7ab52aef14cde0a3c01872fb0e31c80d5eb211549f4a3a5 +size 441905 diff --git a/eval/onestep_L9_latency_s1000/eval_info.json b/eval/onestep_L9_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..296a7cc2885ec31436aa9bf02837b1487b86a206 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 19.999359443596166, + 19.999260995867907, + 0.16969968944801161, + 19.99916872142048, + 19.999248451303757, + 19.999095324331996, + 5.0175277011959105, + 20.00101121211827, + 19.99934821188624, + 5.001776450801087, + 7.317012056654097, + 20.000117386195186, + 20.000448377677145, + 19.999418627788312, + 19.998813395962753, + 19.99968777013118, + 19.998853068013222, + 19.999490301127867, + 19.99945697448623, + 19.999919303268346, + 19.998779613009336, + 19.998635179619804, + 19.999149342407325, + 9.999215220305738, + 19.999808134879526, + 19.999375436326204, + 19.998683241697425, + 19.998923655425102, + 20.000678389369963, + 19.99884907499201, + 19.999485762524003, + 19.99901790376478, + 19.999985571674, + 9.9988365188051, + 19.99884840898008, + 19.9998488379103, + 20.000330514358623, + 20.000726189437717, + 19.9984816471248, + 5.212851620546819, + 0.1809811312046784, + 19.9999126427944, + 20.00068752891362, + 19.999714274971524, + 19.9986330277204, + 19.999797044586114, + 9.999278546372441, + 20.000046556949766, + 19.999803923428153, + 19.99973542424875, + 19.999064007721177, + 19.999331023812804, + 19.99956800503606, + 19.999099445084582, + 0.06036721083247687, + 19.998790033806955, + 19.999487690981077, + 19.999599667710445, + 20.000116869478436, + 5.134582993802715, + 19.999198522121777, + 19.999059329160392, + 5.1789045161254075, + 19.999816522770438, + 0.09614503689889431, + 20.00010078957348, + 5.203987284346816, + 19.999293639776134, + 0.015672518267523805, + 19.99949555919158, + 0.045256495181152934, + 19.999329603212466, + 19.99983307319605, + 20.00032031761795, + 19.999146506158695, + 20.000800541517314, + 20.001018927360782, + 19.999424903345698, + 19.999767241816905, + 19.999483460168285, + 20.000934922132792, + 19.99861229731219, + 20.000253419567237, + 19.99885672390546, + 19.999218232991893, + 20.00151456994752, + 19.999555260050165, + 20.000364504660066, + 0.05853524793204912, + 0.43051551624450524, + 19.99912046452133, + 19.999901021249865, + 19.99879886123959, + 20.00045392690612, + 19.999648792322397, + 19.99926020373648, + 19.99929472310314, + 20.000848674876593, + 19.999490669613785 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 1.5799062427433042, + 10.0, + 10.0, + 10.0, + 1.572105177345842, + 10.0, + 10.0, + 1.5426167489175688, + 4.680468469741963, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 4.5409430678048635, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.6622748906443032, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5872731461243368, + 1.4312093716010765, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 4.495710758562604, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2199411092210652, + 10.0, + 10.0, + 10.0, + 10.0, + 1.530094981022711, + 10.0, + 10.0, + 1.5836988651126274, + 10.0, + 1.3143775099622959, + 10.0, + 4.820429852019626, + 10.0, + 1.2369962374326884, + 10.0, + 1.1728111973047286, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.1108927917213065, + 1.56209607202013, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + false, + true, + false, + true, + false, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 96.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 92.0, + "pc_nested_top": 85.0, + "pc_released_top": 85.0 + }, + "n_episodes": 100, + "n_success": 82, + "pc_success": 82.0, + "pc_success_ci95": [ + 73.33264161369925, + 88.29977450105363 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 17.090887953336736, + "avg_max_reward": 8.58643846489303, + "pc_success": 82.0, + "n_episodes": 100, + "n_success": 82, + "pc_success_ci95": [ + 73.33264161369925, + 88.29977450105363 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 96.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 92.0, + "pc_nested_top": 85.0, + "pc_released_top": 85.0 + } + }, + "overall": { + "avg_sum_reward": 17.090887953336736, + "avg_max_reward": 8.58643846489303, + "pc_success": 82.0, + "n_episodes": 100, + "n_success": 82, + "pc_success_ci95": [ + 73.33264161369925, + 88.29977450105363 + ], + "eval_s": 1852.8634853363037, + "eval_ep_s": 18.52863487482071, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 96.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 92.0, + "pc_nested_top": 85.0, + "pc_released_top": 85.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ea03c133c101f787f247e82aaf4c5ebcc5d38922 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7f875f14a0508e47218620a2d6180e83bc8519773a168386fd55eff25eca30 +size 501268 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..159f1513cf9a8109439055d59c74765bf44e4217 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b839ed99ff831af6594ab1a4e58ed3dcef748454d33f788644537bfae7b2803e +size 416007 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..68349bf43e802638232eb6fb0e8a3abd1c1c183a --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da7e2368fd3e5a1ce2b04d63ca977be4506af61ea0e44527663a984b96f89f5 +size 511907 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e84a4bb969ab25749a5aafa1bd74bd645e5a86c8 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afb6c990feb78051155432b19605b8329a4b878e8efaa19ccf5cb883a838225 +size 1168379 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fe9436157095280acf32c2690c9e8ca926d2bd56 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70386133eb3e7ee52d9349edc5339bb1b5db58082a63446ada99bebd1807bcf6 +size 480697 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..956cf02db164c1c2dbe721a7a85c584dce3b2978 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8c1fabb4a6780fdec61b078a208167eea88f75e5a21d75a3ef8a0dada56dde +size 481677 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3384d3a32efbb1d24246aa8d34acf88a82ea9dcf --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37fb85dc09a2d77ac6e705d192d49c4afaa0a752e6b6f281787c398c60100e83 +size 467434 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0d35e54a843bde2f4a658c054c4706e5c54557e7 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b0c0490f692a69de8986ecfa5f3b8340c5b524054a2e3ccbf2bce5e1c08601 +size 1151794 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fa6241b08d4cb40a681d3656eb9489d82d451ad2 --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7291fc15613fee75f8613191b803991bd51246b16a6462c08141ade88a69845d +size 426604 diff --git a/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a69a10583eda64361d52ed4e6e3428851368fedd --- /dev/null +++ b/eval/onestep_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7611cc3371e511b4463f14a6f591215beae515d1a4540fdcef08089a55a250ea +size 700621 diff --git a/eval/onestep_L9_latency_s1001/eval_info.json b/eval/onestep_L9_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3cd83565516221839943493622a812b5e7ee594e --- /dev/null +++ b/eval/onestep_L9_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.999375854620023, + 19.999260995789665, + 19.999186142679008, + 19.999328652021042, + 19.999264369363438, + 19.9990938982538, + 19.999424750624478, + 5.241700213100286, + 0.01750153692958989, + 19.99943717423259, + 0.08175109870999586, + 20.000121495770266, + 20.000437972920754, + 19.999416637112883, + 19.99903915133305, + 19.999693708091314, + 19.998860752423372, + 19.998961847955385, + 19.999456975116473, + 19.99990686367106, + 19.99877961471981, + 0.1319309204812975, + 19.999150829999294, + 19.99966584226935, + 19.99974479026242, + 19.999377856886927, + 19.99975036116928, + 19.998804131560927, + 20.000657917673575, + 5.430710478701693, + 19.999468386827225, + 0.086236099700572, + 19.99995855716562, + 20.00025308067441, + 19.99858548961103, + 19.999909585331796, + 20.000316508529497, + 20.00075664107522, + 19.9989587873467, + 19.999599449629468, + 19.999820266025882, + 19.99832065039298, + 20.000750681042824, + 19.99926295814083, + 19.998626341227947, + 19.99914217828817, + 19.99981535287756, + 19.999976742175456, + 19.999791579455845, + 19.99968949128065, + 19.999064007721174, + 5.474716669412838, + 0.008478176737572674, + 20.00084637111377, + 19.99853482518424, + 0.06558869824818148, + 9.999261489342583, + 19.9996009137107, + 20.00017077173147, + 19.999680032197613, + 0.08672146415105364, + 5.334138868748238, + 20.000039595554824, + 19.999817208775625, + 19.99897880349801, + 20.00037674664788, + 19.999455383975835, + 19.999324297500724, + 19.999261797101013, + 19.99938638898243, + 19.999925061907142, + 5.215970132043428, + 19.99982608582196, + 20.00034013218114, + 19.999146506158695, + 20.000670237269787, + 20.0009192489523, + 19.99942491114524, + 19.999732540672678, + 19.9994375289781, + 20.00084692864347, + 19.998604049863633, + 20.000269664011668, + 19.99885672390546, + 19.999214332063936, + 20.001562701684456, + 19.99953949421929, + 20.00036177886811, + 9.999056032214233, + 0.004158385354888217, + 19.99912818445514, + 0.016853131012116718, + 19.998820036538, + 20.000453516438654, + 19.99963819748133, + 9.99926020373648, + 0.029728599840605052, + 20.000921883310372, + 19.99945999895808 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.566937921168336, + 1.573095540926229, + 10.0, + 0.027529771844573947, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 4.887080734392489, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5929737076122055, + 10.0, + 0.0236413442473572, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5418262931024063, + 1.1109523130112677, + 10.0, + 10.0, + 0.023934272359628306, + 1.5886431311270144, + 10.0, + 10.0, + 10.0, + 1.2101554291139813, + 1.5669799356986784, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.544594556478624, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.643425709938047, + 1.5698784478920076, + 10.0, + 0.02668749056633779, + 10.0, + 10.0, + 10.0, + 1.622362829896217, + 1.3396692882042576, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + false, + false, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + false, + true, + true, + true, + false, + false, + true, + true + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 93.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 93.0, + "pc_picked_top": 91.0, + "pc_nested_top": 85.0, + "pc_released_top": 85.0 + }, + "n_episodes": 100, + "n_success": 82, + "pc_success": 82.0, + "pc_success_ci95": [ + 73.33264161369925, + 88.29977450105363 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 16.97193801073541, + "avg_max_reward": 8.444603687175798, + "pc_success": 82.0, + "n_episodes": 100, + "n_success": 82, + "pc_success_ci95": [ + 73.33264161369925, + 88.29977450105363 + ], + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 93.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 93.0, + "pc_picked_top": 91.0, + "pc_nested_top": 85.0, + "pc_released_top": 85.0 + } + }, + "overall": { + "avg_sum_reward": 16.97193801073541, + "avg_max_reward": 8.444603687175798, + "pc_success": 82.0, + "n_episodes": 100, + "n_success": 82, + "pc_success_ci95": [ + 73.33264161369925, + 88.29977450105363 + ], + "eval_s": 1504.8426790237427, + "eval_ep_s": 15.048426792621612, + "video_paths": [ + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_0.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_1.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_2.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_3.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_4.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_5.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_6.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_7.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_8.mp4", + "/dev/shm/d1b_4/out/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 93.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 93.0, + "pc_picked_top": 91.0, + "pc_nested_top": 85.0, + "pc_released_top": 85.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..16e4fd04a54242613c67d398fa381d365abcba81 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc6744e3f23f0a2efb77979ee5a95ab432cfba81d000c1ce5b4cf28cd60144c +size 816178 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..01c7c834fc9fe0e0e9d42126a519e3f4940ecd4a --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9571d938e948927795c7134ec3bff7f3c9d5aabf3167a38bbd48c2cf3449f75c +size 424602 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0690c5f6d53ad0faa3ffa9d6f0e26eee12ea1745 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f13c7836ff2f5910871f49d7964b8dfa0cb5e2111b80ee1099b762bc524e67a +size 507592 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e637706d80f10fabf118077b57c9cf277e0f7335 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e07e7e9b10d14d2fe3b1355f7e196a25f75398c037270a0c6cc44872c91562 +size 473158 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cf42141439026e6f7315406d0cf85a3036ee8ba7 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ae7c6e1b8f7ab5f1dfda3672e1ca4b415871df49929c21eee40ab9efc51bfb +size 678083 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5330d0cec971364436454ea1372c7c576874018e --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fae33cac6ad4d48886398287ec6d2d7f42b319daadf785aea348f92d6a39620 +size 485421 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0820b4a0814009c0c967e67008f798641b86d352 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42740c9963c850b38d1661f59b7ded2da5eda0837184d2248fc8170ac3f2d89 +size 468154