diff --git a/.gitattributes b/.gitattributes index 08b37219b2341cecf74ab64ff472cc01e610cccb..a8bf60fd8a681c74e083e8ed034c80773f3759c3 100644 --- a/.gitattributes +++ b/.gitattributes @@ -270,3 +270,156 @@ eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff 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 +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..83115a45ce37e6003c73a25af86586930f79e84f --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01c7f36ca65971d50edd860134d4eb34a8e6c6969d3b9957337e899d2316ff0 +size 444437 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..38a29a48bc5410d9971d7ac04f244816623c3bd0 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581595f9a8146554c1467fc4a2c2a1be9ab659910cca96f0ff6addb01a7b8db4 +size 1102600 diff --git a/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5246ffeecc9624d802ec5b9e24a18b723c35f815 --- /dev/null +++ b/eval/onestep_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69205f43530b22cfbe3b069efcf6242564e059217ec8076013b52fdd826a13aa +size 899793 diff --git a/eval/onestep_L9_latency_s1002/eval_info.json b/eval/onestep_L9_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..71ca14869096b9348dbb92dc607e490650e2afa8 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 19.999381830285596, + 19.99926099578967, + 19.999186156814947, + 19.99924220089251, + 19.99927725218766, + 5.210222432851715, + 19.999397744761175, + 20.00107326546184, + 19.99934925317423, + 19.999434888404764, + 5.0372071400747265, + 20.000146106243882, + 20.000439771030372, + 19.99942795779771, + 19.999014424202844, + 19.99969892235289, + 19.99886767696498, + 19.999559590434252, + 19.998809129351322, + 19.99997185080882, + 19.998779613009336, + 5.0256246282042785, + 5.016712872450915, + 0.013896743131390887, + 9.998917266235793, + 19.999375410812373, + 19.999780368986684, + 5.00210278875055, + 20.00063627748843, + 5.303415815190468, + 19.999478402026845, + 19.99901895881016, + 5.253439699641675, + 20.000261647892057, + 19.998585489611024, + 19.999835113386734, + 20.000303579741143, + 20.0007245129401, + 19.99890602110766, + 19.999600834079164, + 19.99981684929417, + 19.999812520110055, + 9.998815236187532, + 9.999262958140829, + 19.99862522659562, + 19.99979622624218, + 9.999278546372441, + 19.999986150091722, + 5.225417947428648, + 19.999664818408455, + 19.999063895279864, + 19.9992428663852, + 19.99963026625176, + 20.000910393890738, + 0.1753017849251003, + 19.99881595816126, + 19.99947442731673, + 19.99961014856899, + 20.000129313047132, + 0.0317442869075949, + 19.999198647858694, + 19.999062474216654, + 20.000037532408186, + 19.999818707627323, + 0.25328348763474806, + 20.000377541093243, + 19.999466759622653, + 19.999343823861786, + 5.155826066310019, + 19.99939515119436, + 0.10515782950336483, + 19.999329601004852, + 19.999839955484966, + 5.793135990542415, + 19.99934740964826, + 5.148721336411404, + 20.000913435706696, + 19.99942491635393, + 19.999753799498524, + 5.569955383677309, + 20.000846740822418, + 19.998606344228882, + 20.000205955012692, + 0.0386955600029375, + 19.99921489892706, + 20.001552294565222, + 19.999515660363762, + 20.000343338433762, + 19.999056032214234, + 19.999290020590195, + 19.999130599877557, + 0.016028199604928184, + 19.99879860774173, + 20.000609853859814, + 19.999647121801825, + 19.99933607452104, + 19.999332501962165, + 0.20330954099155263, + 19.99948453634248 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5511025500592377, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5922158854537765, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5789757566215066, + 1.5762887866482813, + 0.021818657359084837, + 1.5843190437084038, + 10.0, + 10.0, + 1.55205474779866, + 10.0, + 1.5806205925839563, + 10.0, + 10.0, + 1.5662119986782383, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5986918422916432, + 1.5955407757483793, + 10.0, + 10.0, + 1.582410322944652, + 10.0, + 1.5858252952177931, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.206986202622235, + 10.0, + 10.0, + 10.0, + 10.0, + 0.0223800830844344, + 10.0, + 10.0, + 10.0, + 10.0, + 1.307150233019747, + 10.0, + 10.0, + 10.0, + 1.5503963253839455, + 10.0, + 1.566999337184818, + 10.0, + 10.0, + 1.5756626744336046, + 10.0, + 1.5771593485984907, + 10.0, + 10.0, + 10.0, + 1.584883728400907, + 10.0, + 10.0, + 10.0, + 1.3246894560042615, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.032811044257366806, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.383793893767814, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + false, + false, + true, + true, + false, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + false, + true, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + false, + true, + false, + true, + true, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + 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": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": 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": 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": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": 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 + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": 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": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": 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 + } + ], + "pc_picked_middle": 94.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 93.0, + "pc_picked_top": 86.0, + "pc_nested_top": 80.0, + "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": 16.235463588587447, + "avg_max_reward": 7.920989885818712, + "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": 94.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 93.0, + "pc_picked_top": 86.0, + "pc_nested_top": 80.0, + "pc_released_top": 80.0 + } + }, + "overall": { + "avg_sum_reward": 16.235463588587447, + "avg_max_reward": 7.920989885818712, + "pc_success": 76.0, + "n_episodes": 100, + "n_success": 76, + "pc_success_ci95": [ + 66.76766365018553, + 83.30867444305122 + ], + "eval_s": 1706.7742207050323, + "eval_ep_s": 17.067742211818697, + "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": 94.0, + "pc_nested_middle": 93.0, + "pc_released_middle": 93.0, + "pc_picked_top": 86.0, + "pc_nested_top": 80.0, + "pc_released_top": 80.0 + } +} \ No newline at end of file diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4148253d251a97f16e0f1252075a44d7262677b2 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370c2541527aa74c15b70809a056437573e796cb9a8d102bc4c21c8e8681fdf9 +size 493521 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..95532032e436df193f3970b175b80872c0ddea52 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23c2b10c9118810201a017b040d8a11b4b7c663deb414a042db7fac8f5819c8 +size 431046 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a93185c33ef3ece68dbeeb3060d8f287c6d6de8c --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d3ac16e3998dfba625622ceace8bb051f4eaa9661d42034c18fa60c3f976175 +size 515153 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3f5fa37804910579a9fb656534d09e356a32e0ef --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce03b9bbdbbe965b38a362566de0fd24ba1c655242ba844fee9b0db8a1b6cd5 +size 468417 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..010148ba4b3c24819dccea0e3ff47e9a82c64df4 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304d43954e1e057543dfcc8d6e1febcbd00ce2f0db42275168ff63e8091f256b +size 487575 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c0f2309fca6cedbc6304e66eba7d8509f89d56c8 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bf3409433e3dffae3ed45c077d6d0cca1d32a49d9292687fe30bff4a1baddf3 +size 478497 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f3eba744aeac42b9093d9686aa34aca8bf7ba894 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffba45942f5000aabbf6287d69f0a0d4c6c120b0b5aebeccd1f6742980a1e8d +size 971488 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7acaace100b96744148d1da1a15078bd2db8e830 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6dbd67810b049e1d5a851edfeac2379adecd05b7cadf08ba8811c6cb61ece5 +size 442426 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..86c29d6461c0201a018defb732fbbbb2167be7b8 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ddc56251bca4caacd0b267e7315b81af43f9180855ca4915f79d93d168ebc2 +size 433957 diff --git a/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c4804d68102329ad770891c3128da4d358650d13 --- /dev/null +++ b/eval/onestep_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae95fd83c6ed83a1a9fd18060749c0eaaa0049240ebff5134a6bdb72d19b8760 +size 453622 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/eval_info.json b/eval/onestep_k2_L0_latency_every4_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ea942ed606d4db9d1b2c2aff339fa96f5168682e --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974173766371, + 0.47784831470642786, + 1.524630624708278, + 19.999186142679008, + 5.581223706639339, + 0.44596482989271435, + 0.5112463150569002, + 19.999453880001358, + 0.5044964043235197, + 5.308488782183467, + 5.001853818983394, + 0.3615288165566485, + 20.000213271038408, + 20.000444106816353, + 19.999410523891093, + 0.45395031956237775, + 19.999776083259476, + 5.678536455641254, + 5.606700784137698, + 5.035464683003372, + 20.000055952431975, + 5.734876511919275, + 5.5079739990505345, + 19.999150829999298, + 5.004038947666294, + 5.517446889593854, + 19.999375445092774, + 1.748025154765867, + 0.01866262266997365, + 20.000668398586754, + 0.4186576904071896, + 0.016481161206467587, + 5.598900555504882, + 20.000013313600235, + 20.0003184986897, + 5.497702476929969, + 0.4594347223886809, + 20.000421259801445, + 5.411092027519577, + 5.023277430828251, + 19.99966026854598, + 19.999830637087314, + 19.999984135529772, + 20.000910318435587, + 0.47614779535878393, + 7.348710065802603, + 19.9997965550368, + 19.99985618845222, + 20.000101093333544, + 20.000028320829017, + 1.6399307612994884, + 0.018128697399505733, + 19.99933114647409, + 19.99952992429792, + 20.001045194101188, + 5.521287656534865, + 5.024300115242705, + 19.999496277408465, + 19.99964243247799, + 20.00014676651766, + 19.999680032192366, + 5.446679729336991, + 5.446484599905283, + 0.18741556461456643, + 19.999853803972552, + 5.584167399936099, + 20.000308084476114, + 0.024079175431345967, + 5.025029665557845, + 0.4852724269698284, + 0.5112126413271227, + 19.999847030301044, + 0.49957249782293345, + 19.999826460896312, + 20.000476040802212, + 3.9991465061586946, + 20.000915603492142, + 0.5274029599795765, + 5.534144016332119, + 0.4537998338414756, + 5.035200863087792, + 20.000877260857546, + 5.009010750285392, + 20.000251636009754, + 0.02903964114842994, + 19.99921706197396, + 20.001529127270675, + 5.526628437371892, + 20.00039925301589, + 5.020897744362597, + 19.99929003258338, + 5.227504734191008, + 0.27437314471472307, + 5.008772106278372, + 20.00060785423233, + 19.999700806671953, + 0.4605507821636188, + 0.5534568556588846, + 0.09683918155448501, + 19.999436288278332 + ], + "max_rewards": [ + 10.0, + 0.02618919417233856, + 1.0998921019609256, + 10.0, + 1.5600441274860017, + 0.02586042244831732, + 0.02363933038716748, + 10.0, + 0.029109890470405464, + 1.5587777602034265, + 1.563467947302231, + 0.027212268514458793, + 10.0, + 10.0, + 10.0, + 0.02978524445780628, + 10.0, + 1.5581554542102671, + 1.5690087209291579, + 1.5778992026580427, + 10.0, + 1.572679729966428, + 1.5677938976070789, + 10.0, + 1.5557364665326543, + 1.569172258611364, + 10.0, + 1.3093951717429975, + 0.024778418086635612, + 10.0, + 0.030806633382829407, + 0.039904106265859385, + 1.5587285003675158, + 10.0, + 10.0, + 1.5625339392853976, + 0.024703641496029438, + 10.0, + 1.5918044155341304, + 1.5698199849210563, + 10.0, + 10.0, + 10.0, + 10.0, + 0.02472173556385726, + 1.5796853838930636, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2086815412057135, + 1.2026648613891597, + 10.0, + 10.0, + 10.0, + 1.5614152587625814, + 1.5329494136511879, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5543121280974104, + 1.5620747693013688, + 1.2922933552008165, + 10.0, + 1.5657160361239473, + 10.0, + 0.040597095988990084, + 1.570858103859616, + 0.025390417499063567, + 0.025626124142886675, + 10.0, + 0.02658936583768634, + 10.0, + 10.0, + 1.540815835852942, + 10.0, + 0.02990358961709938, + 1.5596099996985144, + 0.028415601707593163, + 1.5387191096142558, + 10.0, + 1.578322845626213, + 10.0, + 0.025262423327236605, + 10.0, + 10.0, + 1.5751990506292413, + 10.0, + 1.5799552284398863, + 10.0, + 1.577128959429058, + 0.022986843890792974, + 1.5635062952811758, + 10.0, + 10.0, + 0.025352504720381974, + 0.024873997286993577, + 1.344035390522023, + 10.0 + ], + "successes": [ + true, + false, + false, + true, + false, + false, + false, + true, + false, + false, + false, + false, + true, + true, + true, + false, + true, + false, + false, + false, + true, + false, + false, + true, + false, + false, + true, + false, + false, + true, + false, + false, + false, + true, + true, + false, + false, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + false, + true, + false, + true, + false, + false, + false, + false, + true, + false, + true, + true, + false, + true, + false, + false, + false, + false, + true, + false, + true, + false, + true, + true, + false, + true, + false, + true, + false, + false, + false, + true, + true, + false, + false, + false, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_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": 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": 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": true, + "nested_top": 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": 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": true, + "nested_middle": 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": 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": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": 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": 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": 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": 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": 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": 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": true, + "nested_middle": 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": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": 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": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": 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 + } + ], + "pc_picked_middle": 79.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 72.0, + "pc_picked_top": 46.0, + "pc_nested_top": 44.0, + "pc_released_top": 44.0 + }, + "n_episodes": 100, + "n_success": 44, + "pc_success": 44.0, + "pc_success_ci95": [ + 34.6720266301608, + 53.77189534832302 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 10.48443495474621, + "avg_max_reward": 4.934145620951614, + "pc_success": 44.0, + "n_episodes": 100, + "n_success": 44, + "pc_success_ci95": [ + 34.6720266301608, + 53.77189534832302 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 79.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 72.0, + "pc_picked_top": 46.0, + "pc_nested_top": 44.0, + "pc_released_top": 44.0 + } + }, + "overall": { + "avg_sum_reward": 10.48443495474621, + "avg_max_reward": 4.934145620951614, + "pc_success": 44.0, + "n_episodes": 100, + "n_success": 44, + "pc_success_ci95": [ + 34.6720266301608, + 53.77189534832302 + ], + "eval_s": 2615.855697631836, + "eval_ep_s": 26.158556981086733, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 79.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 72.0, + "pc_picked_top": 46.0, + "pc_nested_top": 44.0, + "pc_released_top": 44.0 + } +} \ No newline at end of file diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b541fba8d9147dbca1e777604fa27c45e6d7cc5c --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d45f17f426180e77bf80a5da74096fa34a1fde90db472a546a2a7ec0487c215 +size 724898 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..94585b93809f7d539fe2d6a1841d9cd637a96ec7 --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40cb18eb7fc15b6f9b27865d894becf6c4b451ea65deff55e4a0660b288c593d +size 304274 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e543f5ad96edf1847d0cb1748b3025b2cf5c5b11 --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17dd7150e024637ce6f391eb207d5eb9daad71259a9f699483edd1c85521c116 +size 637876 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8c20263174bc4524a93c089cd344217481b4104a --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6b91f64093251aa5c1a038ea799a6bc6183b75f84170f81f17cc8e4a125848 +size 475993 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cca1dd98e770afff9cbf67b92f73e54659bf80d7 --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4611596a1b698a99a12faa1db2da7733b36c83ecf09fa09c6eba13456ad7e0a2 +size 810561 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b8ff93e644d44b100599493be4a5aa9adf992bad --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf830d57db529fc1aa3ca8754dc196d5a916d9c2385802796562e1c62fe04f41 +size 462482 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b02a126afa5ad5f6e653aaeb043df68bc1d7dc21 --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2e71938081744055271bd540ffa08626c0e7aef40886c6f158c390c21a8d2c +size 428002 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..88d57bb1b7797804938434090fffd271a861926c --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88fbd69ff866b848f53be42c591f7a8dec58d55df19b908c0298230dc986902 +size 424896 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b4ccf8fc0c0b8a38442df4ffb94f70adbae6f92c --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3cd82e223fe83c45cd6b5d9cc2abcc2795e4e9b6cbcf9e3bef2937c2f3e56e +size 622574 diff --git a/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..53ac0a4869280f4bf144ce94639045ed0d354ab1 --- /dev/null +++ b/eval/onestep_k2_L0_latency_every4_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e0f9ae183c4294db47bcfca23efe89c9b7bb771606a14a57be7a6da7d447a9 +size 571395 diff --git a/eval/onestep_k2_L0_latency_s1000/eval_info.json b/eval/onestep_k2_L0_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7915ed6585b4dfcbcbf04f7ce2b8b2472af099a3 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 7.428929029398599, + 0.47792078855478626, + 1.5147284836616794, + 19.999186142679005, + 5.010588264929659, + 0.2347849393998398, + 0.5116857024756318, + 1.9308020091577773, + 0.5055358676843392, + 5.307697306941022, + 5.001553988534475, + 0.3612030813735405, + 20.00022780754623, + 20.000434678934713, + 19.999410637768804, + 0.45419873573511693, + 19.99976901089616, + 5.679997295729475, + 5.609406756654936, + 5.192335185795452, + 20.00003862112303, + 5.269699105464259, + 5.508041235379563, + 19.999150827613864, + 5.003766914680664, + 5.520161704015198, + 19.999375445092767, + 1.7462605891736147, + 0.018553080802427457, + 20.000683931946202, + 3.9987533547839527, + 0.016677648528669375, + 5.600811541884104, + 19.999992867560017, + 1.629237660959718, + 5.495480773930912, + 0.46043148498349373, + 20.000431023755887, + 20.000723358653282, + 5.022427796549778, + 19.999668231410137, + 19.999829330098887, + 19.99995563865818, + 20.000912139378087, + 0.47618995131716535, + 5.469327108065519, + 19.999793946389524, + 19.99984590416723, + 20.000093147561344, + 19.999877238452562, + 1.6403101319371673, + 1.6800779311355483, + 19.99933114647409, + 19.99955633855795, + 20.001109542038865, + 5.52052006133462, + 8.998319826312354, + 19.9995024285371, + 19.999637188058532, + 20.000160710257454, + 19.999680032192366, + 5.607807850717462, + 5.446465616691066, + 20.000034240854568, + 19.99985877242842, + 5.583574439816464, + 20.00036677819578, + 0.023631775560160606, + 5.02206320038837, + 0.4853078015747233, + 0.5112319426263475, + 19.999851475500456, + 0.49978514228948323, + 0.5008917385666456, + 20.00047166371872, + 3.9991465061586946, + 20.00085893250545, + 0.5389688038175495, + 5.530223391150165, + 0.45373219772216944, + 9.999062375139319, + 20.00098367123113, + 5.008993453424355, + 20.000252019371572, + 0.029046534668496937, + 19.999215071637675, + 20.001528017297602, + 5.527584161568896, + 20.000399467149403, + 5.020816384904787, + 19.999290032583378, + 5.012909511860855, + 0.2743736152418683, + 5.008478758809095, + 20.00058602643326, + 19.99967698710772, + 0.4596656543527947, + 0.5533855815753779, + 20.000931195164135, + 19.999438839616165 + ], + "max_rewards": [ + 1.5806428387197802, + 0.026200354356180178, + 1.0977549091415968, + 10.0, + 1.5617862951286066, + 1.28112457976398, + 0.023646140456798692, + 1.3384292323444231, + 0.02909765539678444, + 1.562877870174645, + 1.564351788455046, + 0.02720938338253298, + 10.0, + 10.0, + 10.0, + 0.029705310079129466, + 10.0, + 1.55727615556264, + 1.563027940131779, + 1.5657246505978608, + 10.0, + 1.574022601323081, + 1.571036870218804, + 10.0, + 1.5565900835418247, + 1.56927954584968, + 10.0, + 1.307865060386269, + 0.024795386927526697, + 10.0, + 1.5788643139720593, + 0.03979909194720821, + 1.5536462451982276, + 10.0, + 1.194263274910879, + 1.56158772785035, + 0.024699527502832996, + 10.0, + 10.0, + 1.569070548740992, + 10.0, + 10.0, + 10.0, + 10.0, + 0.024731414716019806, + 1.5794355186921842, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2086310222904144, + 1.1558316572389624, + 10.0, + 10.0, + 10.0, + 1.5561545860450905, + 1.518154699270435, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5420520846196002, + 1.5663026675252891, + 10.0, + 10.0, + 1.5687638926047835, + 10.0, + 0.04087505370775779, + 1.5696031808744981, + 0.025341723395503668, + 0.02564079883627568, + 10.0, + 0.026202999192187604, + 0.029992401656748435, + 10.0, + 1.5649405921024848, + 10.0, + 0.02990684960737211, + 1.5405165720443932, + 0.028835119348747384, + 1.5660817216146672, + 10.0, + 1.578784333901958, + 10.0, + 0.025865783511835216, + 10.0, + 10.0, + 1.5734941263114326, + 10.0, + 1.5792153952869556, + 10.0, + 1.5608287966849594, + 0.023009196646197827, + 1.5682758962705705, + 10.0, + 10.0, + 0.025388589542434503, + 0.02491281675896262, + 10.0, + 10.0 + ], + "successes": [ + false, + false, + false, + true, + false, + false, + false, + false, + false, + false, + false, + false, + true, + true, + true, + false, + true, + false, + false, + false, + true, + false, + false, + true, + false, + false, + true, + false, + false, + true, + false, + false, + false, + true, + false, + false, + false, + true, + true, + false, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + true, + true, + false, + false, + true, + true, + true, + true, + false, + false, + true, + true, + false, + true, + false, + false, + false, + false, + true, + false, + false, + true, + false, + true, + false, + false, + false, + false, + true, + false, + true, + false, + true, + true, + false, + true, + false, + true, + false, + false, + false, + true, + true, + false, + false, + true, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_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": 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": 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": 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": 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": 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": 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": 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": 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": 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": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": 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": false, + "nested_top": false, + "released_top": false + }, + { + "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": 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": 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": 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": 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": 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": 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": 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": 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 + } + ], + "pc_picked_middle": 79.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 71.0, + "pc_picked_top": 46.0, + "pc_nested_top": 45.0, + "pc_released_top": 44.0 + }, + "n_episodes": 100, + "n_success": 43, + "pc_success": 43.0, + "pc_success_ci95": [ + 33.733298524110104, + 52.784610450787675 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 10.453956822824878, + "avg_max_reward": 4.860621448723602, + "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/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 79.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 71.0, + "pc_picked_top": 46.0, + "pc_nested_top": 45.0, + "pc_released_top": 44.0 + } + }, + "overall": { + "avg_sum_reward": 10.453956822824878, + "avg_max_reward": 4.860621448723602, + "pc_success": 43.0, + "n_episodes": 100, + "n_success": 43, + "pc_success_ci95": [ + 33.733298524110104, + 52.784610450787675 + ], + "eval_s": 1892.6327953338623, + "eval_ep_s": 18.926327962875366, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 79.0, + "pc_nested_middle": 73.0, + "pc_released_middle": 71.0, + "pc_picked_top": 46.0, + "pc_nested_top": 45.0, + "pc_released_top": 44.0 + } +} \ No newline at end of file diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..707505e22156d8a7eaf7bdbb601da956494c8a7f --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:434278ab48cbe6b44f294503d2b7feb25cb4dce3fcf6daa26adbf326fb33de8a +size 711211 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0401d36b90a43513e31a53fd3c63000c771dbb67 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384bf93c0ead080adb6d15cf51b119bb4494d3ce64580abe9df31ae0a3fce92b +size 302515 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3c5e0b0fb0d554ccd005b2f13bc6eb6928c872b4 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5382f0e466182a39233f0f1058c9779af38b71c78ab4345ec0560624abd2577a +size 552858 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d19a9e7b34615427b54a08ab27ff45c51fe83da1 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6477a63b63b2777c2a9e038e4e4a6005ff8d45395d9399b0f991069d09a03481 +size 485943 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3e1d2c24c7bcee4c3b4f8eded44ee65019c2c9c2 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:424538e06f06fe2e8f35b590611e6a2eb64cac64c9483502033e8e39ae3d60cd +size 919025 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2e2aa2a6d2eb1d4d3491b78684f274c56f70599a --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:021cf6f2f7f98681de89c1b314bc2805f8ee1fcab20c05095e79c4e84cfa7779 +size 489607 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..931ca0d2c88eab8a2d116e6732103738ead59469 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791a801338ac049eb6cd74e64cf577acf92f5ec2788ac9db18b2334d5114c515 +size 427484 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..aa2a2596164e3dee2b8f1d952a9a200fb6d046e8 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66aa7d306b317d8ec56bc1482bd8ea68bf947c07586c7cd13d589d30c62d632d +size 802065 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7653bba2ced0284a7b8fd4c9ecd15ce0167d99a8 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155b759e7c3e3462699ab3bec7c45797f2caedf1d68ec0453c65387b80e8ca82 +size 630832 diff --git a/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6bb03f5fd37a617000becee8676c058ff3cd5920 --- /dev/null +++ b/eval/onestep_k2_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371a0a332924dcf0de7caa845397ac5d07907cdbab20afae937ad11df61a461d +size 574510 diff --git a/eval/planbind_L0_latency_s1000/eval_info.json b/eval/planbind_L0_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..2dd4d773164841c6ee8b3cf9788f7442a82f7e39 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 19.99935841492967, + 19.999261025275832, + 19.999071268212482, + 19.999245394529865, + 19.999281527896688, + 19.999105499245537, + 19.99938018037566, + 20.00085745377058, + 19.999363880838935, + 19.99944358517986, + 19.998560972989914, + 20.000115160369663, + 20.000431820637672, + 19.99929530569687, + 19.999055322437442, + 19.99969040984746, + 19.998870095944476, + 19.999514792606583, + 19.9994569617986, + 19.999863541024464, + 19.99877961454392, + 19.998645546035803, + 19.999150643094644, + 19.999665839034755, + 19.99974673596423, + 19.999377318965912, + 19.99974321458771, + 19.99880413156093, + 20.000558018361957, + 19.99883791706297, + 19.99879684881501, + 19.999023518758225, + 19.99996952633186, + 20.00039630495765, + 19.998834654108794, + 19.999877021608686, + 20.000235859418822, + 20.00077204239665, + 19.998877635097465, + 19.999645212602537, + 19.999808967335476, + 19.999928847437573, + 20.0007232269416, + 19.99926295814083, + 19.99862862640061, + 19.999798522572608, + 19.999822987580124, + 20.0000211484129, + 19.999843013600078, + 19.999679279081622, + 19.999063927118947, + 19.9992428663852, + 19.999621641657406, + 20.000892306884786, + 19.998539480670367, + 19.998817481154862, + 19.999484601262143, + 19.999601223869345, + 20.000116751070607, + 19.999680094296657, + 19.99919858742801, + 5.126079216097309, + 20.000058933750836, + 19.999780509253313, + 19.998982026335806, + 20.000424256338057, + 19.99945716760096, + 19.99934144244794, + 19.999395726563183, + 19.999535446752382, + 19.999938517697597, + 19.999331837511985, + 9.999084323334248, + 20.000466464514513, + 19.999347334895443, + 20.00067952639138, + 20.00093194233489, + 19.99942490945244, + 19.999738378393484, + 19.999447799062153, + 20.000794004739493, + 19.99859814134053, + 20.00018186645727, + 19.998856723905458, + 19.9992197931518, + 20.00150563129462, + 19.999581572377465, + 20.000350781041377, + 19.999045836700613, + 19.999070368460483, + 19.999118077072055, + 19.999901021249865, + 19.998816545134122, + 20.000549761132, + 19.999631530970458, + 19.99926020373648, + 19.999341096180693, + 20.000887359483624, + 19.999490205280182 + ], + "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, + 1.523685221303437, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 9.765125029522249, + 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, + false, + 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, + 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/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": 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 + } + ], + "pc_picked_middle": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 99.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + }, + "n_episodes": 100, + "n_success": 98, + "pc_success": 98.0, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.75085583708887, + "avg_max_reward": 9.912888102508257, + "pc_success": 98.0, + "n_episodes": 100, + "n_success": 98, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/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": 99.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } + }, + "overall": { + "avg_sum_reward": 19.75085583708887, + "avg_max_reward": 9.912888102508257, + "pc_success": 98.0, + "n_episodes": 100, + "n_success": 98, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ], + "eval_s": 2555.481984615326, + "eval_ep_s": 25.554819853305816, + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1000/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": 99.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9e8c8effdc1cc77cdb498f42691b5b0f75efc517 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164ac6c7799bf2218291cb35ae2e92a5e2d871384b7060619a0c71aefaf6a644 +size 494701 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b7f550da07c25bed5a0c568f4b262e83fdb94452 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f2040e37ab4de2855c25f3ef5d4c2f634b7b14331544a1bd838fb992df1f42 +size 417528 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..854e458acb1cee8c29ea8ddab84e6f57e8ff346b --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d358ca1cd0b5f6aaa8ba65f08611833dae932419b74e3feee42ac28f9a9b6b95 +size 487543 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7926ef11f4735bba1f5165911f1cf608e6724192 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb047254b9cf9eda3e09c44cd66b128316e76a3fe225f18f7d4dfffa14f86a2d +size 488935 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..238487e016fcaca3dbaa428069a5c8d91cda8da0 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6b0b4776713cdaaca3ef62e8d8805535587d05a96963a34e11bbd709207519 +size 483380 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..31a1eb0f7d8a0edea34eab2c3722bfe083c05da2 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f040a86907a4258bcb171cddbf25ffefc3554310f8ce757be8915798cf10a39 +size 496952 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..381d9a5563c1fa7f987239f232a36d45c97bed78 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f2297c0e45a424345aa13e36af75b2f52584548d85e7c370ed7ab5c16ce9a1 +size 453246 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5accd061c1d6b01681bc2d54aac3b67585aae3b3 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca129a53f1c512cc64cff6332b216d1b7a8a73e0b214ce83d23d281ae738559 +size 434703 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e07242aacd5caf03bbf239f13c861caa3d808ae1 --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bbea364c2c2e97840d7bf12887c163597116ed9fc6cf13cbc98274295740ba +size 417548 diff --git a/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c9e7d31b49d1a2f5f37f8afe445969cc46ab5e8e --- /dev/null +++ b/eval/planbind_L0_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b550e0f3fa2aae0751397afbb39da0836f54eaeac6b74820daef71b76a4725be +size 452225 diff --git a/eval/planbind_L0_latency_s1001/eval_info.json b/eval/planbind_L0_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e6249e36d89d2d46c25128fb9ba71cc53318ba37 --- /dev/null +++ b/eval/planbind_L0_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741720462847, + 19.999358887434706, + 19.999261015937265, + 19.999186142679008, + 0.05368315656705369, + 19.999307707704602, + 19.99910429224893, + 19.999367567797666, + 20.000943814543977, + 19.999349172415595, + 19.999462307025535, + 19.998560000642804, + 20.000048427842565, + 20.000466886470708, + 19.999295305696872, + 19.99903184045035, + 19.99969032606847, + 19.998853591314244, + 19.99954478404906, + 19.998809129351322, + 19.999999823602344, + 19.998779617480018, + 0.08933628057346188, + 19.99915059737443, + 19.999665861921354, + 19.999782342404956, + 19.99937535035906, + 19.999815438488152, + 19.998924042000414, + 20.000584699595002, + 19.998861635679773, + 19.99945798750864, + 19.999019092122857, + 20.000062903718092, + 20.000311864815963, + 19.998816232338704, + 19.999278899879666, + 20.000437572468126, + 20.000740604356118, + 19.9988815920665, + 19.999608321498688, + 19.999818150135745, + 19.99989814282083, + 20.00060060374306, + 19.99926295814083, + 19.998624071246617, + 19.999793912487437, + 19.99980851808533, + 19.99997395993201, + 19.99987507728895, + 19.999668013298738, + 19.999063668135545, + 19.99933111781715, + 5.106211446463176, + 20.000920388904376, + 19.998548067355987, + 19.998831686535237, + 19.99952914431644, + 19.99961857762955, + 20.000092087810422, + 19.999680036331828, + 19.999198385466787, + 19.999050312103204, + 20.000048234016585, + 19.99982613726147, + 19.998953020258714, + 0.06160726017165996, + 19.99944876317713, + 19.99931421317634, + 19.999396431756225, + 19.99951989579786, + 19.999854692888665, + 19.99932960815314, + 19.999826601273494, + 20.000350860280676, + 19.99934736435374, + 20.00071472804224, + 20.00100940326423, + 19.998842547616235, + 19.999696554807002, + 19.99943987380674, + 20.000907106611642, + 19.998606133205257, + 20.00024116651325, + 19.99885672390546, + 19.99921599299423, + 20.001537743321535, + 19.999542879747963, + 20.000347397521292, + 19.999045544350285, + 19.99907036846048, + 19.999118170297606, + 19.99990103646065, + 19.998784358333594, + 20.000567793510278, + 19.99959537502216, + 19.999335811720016, + 19.99930523163568, + 20.000825302055777, + 19.999466991408873 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 0.027851175242612047, + 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, + 1.2755723882368173, + 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, + 1.5261001491985313, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3634873114749866, + 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, + false, + 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, + 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, + 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 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_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": true, + "nested_top": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": 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 + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 96.0, + "pc_released_top": 96.0 + }, + "n_episodes": 100, + "n_success": 96, + "pc_success": 96.0, + "pc_success_ci95": [ + 90.16292856411208, + 98.43366960084523 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.252721524801828, + "avg_max_reward": 9.641930110241528, + "pc_success": 96.0, + "n_episodes": 100, + "n_success": 96, + "pc_success_ci95": [ + 90.16292856411208, + 98.43366960084523 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 96.0, + "pc_released_top": 96.0 + } + }, + "overall": { + "avg_sum_reward": 19.252721524801828, + "avg_max_reward": 9.641930110241528, + "pc_success": 96.0, + "n_episodes": 100, + "n_success": 96, + "pc_success_ci95": [ + 90.16292856411208, + 98.43366960084523 + ], + "eval_s": 2349.3516421318054, + "eval_ep_s": 23.49351642370224, + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 96.0, + "pc_released_top": 96.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..aca8838598e0472a9458c82aaf8f068359229295 --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2da1696ac76d3130596551e7600a56203cefee1ebdfdbcefb2752783ec5586 +size 500137 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a47d8647f695ea810ba4c702552a9d132e32ed7a --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5514e2d7de4383c3b571aee86b057b7cca5ab1e8f3618e4b251d2f7c47e8e170 +size 427892 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6c40562ba2a9af96561b4c050f5d5258a0d46e84 --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16771cfd9a44794c466dcd541fecf3009a360a4aa27af6d53fb2b7bbe88fafb +size 528114 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..46ebaa013331dac9232d5cf0d730d3ba19503271 --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74bda2a063fd08484ab48950801f433820001472b5b95fbe74a2107730c17758 +size 493400 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5eef92cb7eb48663a693467838688932c66d713d --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352349aab32983a0947f0497d1f3690bd05ace6526a99c53cc3b8b5f27ae3380 +size 872667 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5ff02dd1d82c46483933aed72ba080e307be3bbd --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86480f7f55239a439e82f5d6d7ff8336b941699e3df5da4bbd2bb61bba24154b +size 503669 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..891ece750ce523ff4d5525066113988215273922 --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3d2ae8df5feff95ad6e39a3f19e7195433d4caa69e53d347e52d7e535b88da +size 486411 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..80878596d5bb35d8b1032be69145a9c3916399a1 --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f3ccdfcd80a9fc75399182cbfba75f8b66f685e2e21661a63cfd9a9afcb8bce +size 433548 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..dcfbdab8dfee6fd3ef0ffb0ccf45cc39ec69061a --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c53cbbf2e780a088fc86e1562dc9d2b5689f5649a83f632ad323433bce5095 +size 422397 diff --git a/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e4862d4fdff40fb8d2d9af4c01496519a168782d --- /dev/null +++ b/eval/planbind_L0_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b153a332ff02eb2f1c798245d3854defb74e60f6c57d65d5a3c1ae468addb7 +size 442804 diff --git a/eval/planbind_L0_latency_s1002/eval_info.json b/eval/planbind_L0_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..bb350c0e53de998992a5eabe787d6ac531f028dc --- /dev/null +++ b/eval/planbind_L0_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741731445397, + 19.99936013990518, + 19.99926099578967, + 19.999071268212482, + 19.999271176424102, + 19.999315679302985, + 19.999113109075445, + 19.999376680180433, + 20.00078388706884, + 19.99934602019422, + 19.999443071830868, + 19.998568002926795, + 20.000095531226428, + 20.00045973841203, + 19.99941585941246, + 0.2606333023117089, + 19.99969936582409, + 19.998880277619165, + 19.99956779657283, + 19.999456975116477, + 19.999914258184443, + 5.396319649350642, + 19.99865595379865, + 19.999150707376078, + 19.999665841389522, + 19.999784214959465, + 19.99937529605655, + 19.999802765708026, + 19.998923956303162, + 20.000645874338048, + 19.998840646897182, + 19.99946064014933, + 19.999026430038462, + 20.000039368195512, + 19.9988365188051, + 19.998833241605222, + 19.99985685131287, + 20.000363518791932, + 20.000660381674628, + 19.998833628883485, + 19.99954822391999, + 5.223855837768902, + 19.999979343931532, + 20.000698462963896, + 19.999767241537732, + 0.23825353305463137, + 19.999798904727314, + 19.99983530440132, + 19.999942330552752, + 19.999770996118823, + 19.999671427629178, + 19.999063963405472, + 19.99933114647409, + 19.999667792916348, + 20.000956545561824, + 0.20139838614699823, + 19.99882623136743, + 19.999517794847275, + 19.999606271555173, + 20.000076471546677, + 19.999275931764544, + 19.999198528071794, + 19.999043569943833, + 20.00001235581672, + 19.99974878695262, + 19.999009795047172, + 20.000274109679996, + 19.99945995039899, + 19.999352560069116, + 19.999397838712543, + 19.99960471828464, + 19.999903557829086, + 19.99932960879814, + 19.999835579955764, + 20.00045047098319, + 19.9993471867745, + 20.000742163637895, + 20.000988205764823, + 19.99884254761623, + 19.9997741028639, + 9.999062375139319, + 20.000912485559482, + 19.998598146072624, + 20.00024990236713, + 19.99908081360244, + 19.99921650008868, + 20.001540887940884, + 19.999556376722573, + 20.00033490544731, + 19.999046095541686, + 19.99907036846048, + 19.999112654898028, + 19.999901025101813, + 19.998799235606096, + 20.000584410027376, + 19.999635956805985, + 19.999359381774283, + 19.999346605167815, + 20.00088916982384, + 19.999517821492944 + ], + "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, + 1.1701874034765012, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 4.676323091554756, + 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, + 1.6064638989899915, + 10.0, + 10.0, + 10.0, + 1.213179677362775, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.029410874570075962, + 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, + 1.6329878994655957, + 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, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + 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, + 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, + true, + true, + true + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": 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": 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 + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 99.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 96.0, + "pc_released_top": 96.0 + }, + "n_episodes": 100, + "n_success": 94, + "pc_success": 94.0, + "pc_success_ci95": [ + 87.52318455410406, + 97.22138760368118 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.012848232497035, + "avg_max_reward": 9.503285528454198, + "pc_success": 94.0, + "n_episodes": 100, + "n_success": 94, + "pc_success_ci95": [ + 87.52318455410406, + 97.22138760368118 + ], + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 99.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 96.0, + "pc_released_top": 96.0 + } + }, + "overall": { + "avg_sum_reward": 19.012848232497035, + "avg_max_reward": 9.503285528454198, + "pc_success": 94.0, + "n_episodes": 100, + "n_success": 94, + "pc_success_ci95": [ + 87.52318455410406, + 97.22138760368118 + ], + "eval_s": 3379.0051941871643, + "eval_ep_s": 33.79005194664001, + "video_paths": [ + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4", + "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 99.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 96.0, + "pc_released_top": 96.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..872d0e25e0aa168468609d693cdc65f7ef583f1d --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e81e7a42248b82f604f0f9ae1e2ca610ebb44d448d3c6c6ff23a76c0e843df6 +size 487250 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d05975aaf03cdcdf76953e280ce0a53879ee0cf3 --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eecdafa893a07b36dd107bfbf1c59ec063f6d38f9a8a28fd014dfd71de2abab +size 425298 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..628ca67242729c2e9f5fd6bbba3bab879bbb151b --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea44fce3fb63fde520852024771e14aa6b24ec58627d9061215fd7c73951ecd +size 486018 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8f1813c7d38e7ac644884a663cc0f5c37d682c73 --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b582d8a082c2463757a57edf03189c7d38380a6bf2d6d43d44fc5cc21f8015ea +size 486518 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c85b6b1ad580044bae6f1beff76b08e60069ead2 --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae93c01094a074f6a7a16a95ef465bca19cd5d6f3315c91b184c58190245a3f +size 468123 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..82db194ae7fbdb7637323ac9f36c8072749b1f72 --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d6f5c2954f7debcfaf0ee742cbb806a2d975bbca5e4ae132bb537368d7123a +size 472864 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bac443f484063967d885acb117e37ce21533ee62 --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecfa13533b6fad7df48177b1ccb33b38d84804d6dc6bbdd83b3201114afaeb8 +size 461550 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c2f5f0c2265c6e24c1807654440581c44f31063e --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2342e6c9ad3fc1930a1f32dc4c11c87fa2073f5981634a114f46130ad06a7a8 +size 437603 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1f8fcb85169247b552b2014747c3acf67c72639a --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da746b637d4d751c7e4f6d0e1544a075a5f5bbb6f43a8f7042a976e10e737867 +size 423316 diff --git a/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4ca58aba4cbaee336d66d305ed51b3b2dcb1afcc --- /dev/null +++ b/eval/planbind_L0_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432669addd400e1bc8125f41d5c482a4ba1c6dc4144a5c7e0845339169e965eb +size 445486 diff --git a/eval/planbind_L0_none_s1000/eval_info.json b/eval/planbind_L0_none_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e9507dc2933b8b5462003e732aa1cb9fb7b5d292 --- /dev/null +++ b/eval/planbind_L0_none_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 19.99935174511909, + 19.99926099833951, + 19.999071268212482, + 19.999285903349, + 19.99929602365588, + 19.999164309631695, + 19.999363999152624, + 20.000874228227183, + 0.19424675556384452, + 19.999447596748723, + 19.998414633846878, + 20.000024316433613, + 20.00046498203477, + 19.999467592425294, + 19.999058910181184, + 19.999649949740977, + 19.998909728463577, + 19.99950982043466, + 19.998809129351322, + 19.999870097469383, + 19.998779613009333, + 19.998650562358215, + 19.999150782999482, + 19.99921522030574, + 19.999795648791558, + 19.999385240404745, + 19.99975945222709, + 19.99880413156093, + 20.000538388022893, + 19.998845630842638, + 19.99948793122312, + 19.99900339348179, + 19.999983700084186, + 0.09987609334450087, + 19.99887751732711, + 0.05213748634895499, + 20.000277334584975, + 20.000724652417034, + 19.998916530150236, + 19.999594723765476, + 19.99982067861873, + 19.999860892694784, + 20.000782880754226, + 19.99926295814083, + 19.998629915750865, + 19.99914217828817, + 19.999829693729474, + 19.999950499919503, + 19.999776179596854, + 19.9996500333468, + 19.999064007721177, + 0.46546637383567613, + 0.15368824384483037, + 20.00085676177496, + 19.998550445000724, + 19.998831113168407, + 19.999488370733964, + 19.99918100397128, + 20.000098767492098, + 19.9997003878128, + 19.99857760033889, + 19.99905205860895, + 19.999966150095663, + 19.999766774534578, + 19.998983615005475, + 20.000200827976943, + 19.9995113798401, + 19.999318863163595, + 19.99926179710101, + 19.9995724144502, + 0.2712146749060076, + 19.999337365207886, + 9.999084323334248, + 20.000359373162585, + 19.99914650615869, + 20.000709171633854, + 20.000963560624694, + 19.999424916353934, + 19.99977407177429, + 19.999448066499564, + 19.998987382318816, + 19.998598334392998, + 20.000241169539365, + 19.999116183756485, + 19.99908214351669, + 20.001545010968748, + 19.999597338855892, + 20.000335655572265, + 19.999046033581973, + 19.999070368460483, + 19.99912930495429, + 19.999904666376924, + 19.998810969117, + 20.000578635350728, + 19.99970624305934, + 19.999301508072016, + 19.999330554375163, + 19.99837176591066, + 19.99949647686939 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.1728310175756722, + 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, + 0.03005622345703729, + 10.0, + 1.2847116998361794, + 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, + 1.215437189262341, + 1.1096039834649232, + 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, + 1.1883964301033625, + 10.0, + 4.795226960532834, + 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, + 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, + false, + 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, + 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 + ], + "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": 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": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 99.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 94.0, + "pc_nested_top": 94.0, + "pc_released_top": 94.0 + }, + "n_episodes": 100, + "n_success": 93, + "pc_success": 93.0, + "pc_success_ci95": [ + 86.25048526092651, + 96.56807389327273 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.71190642401312, + "avg_max_reward": 9.407962635042324, + "pc_success": 93.0, + "n_episodes": 100, + "n_success": 93, + "pc_success_ci95": [ + 86.25048526092651, + 96.56807389327273 + ], + "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": 99.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 94.0, + "pc_nested_top": 94.0, + "pc_released_top": 94.0 + } + }, + "overall": { + "avg_sum_reward": 18.71190642401312, + "avg_max_reward": 9.407962635042324, + "pc_success": 93.0, + "n_episodes": 100, + "n_success": 93, + "pc_success_ci95": [ + 86.25048526092651, + 96.56807389327273 + ], + "eval_s": 1409.3879594802856, + "eval_ep_s": 14.0938796043396, + "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": 99.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 94.0, + "pc_nested_top": 94.0, + "pc_released_top": 94.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0d0ca7366f81ba51f5df57fae6cca661b9e523d6 --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e985b3c8d0c1e3e5d4c1c0e21a3535ebde2f372691df56530f64ac207e8be7c6 +size 497807 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..19c7499ee14078e1eb427183a6e6e9cb3eac236d --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ac8ba70c2f50f7c527cf8fdd69a76f85b17479387ecd2465353957a13e1f7e +size 436624 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d05b243506583ce97098f8fbfde1630047895fb5 --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be3ffd73a8b150fc481d38658319b08399239d305b5c23bf5340fdb34f19841d +size 502279 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1be815d82af49df8cca6aecfd18e0399347c029e --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d34176a21d4eee2a3f4f48ca259afe56f4d66bcb56ff2305f4cbf4b98efef7 +size 494861 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..af6884b53905a13e67d6eb65a1c71cc939fed0f5 --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3741b5003e9f7a6700c01d0879c8fdc20c3a5f21fde862a0fffe8c14761f47 +size 505269 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5738f298fcd609ba96977b30b4c6d64cb8ec7ce2 --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ef179ede981c7320ea9cf1e7b3f3edea8d9849336f07fa13d392dc13cad351 +size 493682 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3b59a954fd4e59dfa8400b86ab78eab307d428a3 --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d73dbd7e3f1e91a16852c3f790e04078e8ddc96645b148d0f0dbdbb9cc54642 +size 457967 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d509b805ecbff0c852998eaba1215b0595f799b6 --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6c51a01f7d148e9734d4e1b652b43305ebb9cd12bce682e7b26c8d14e8f413 +size 441243 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5718535af63e6cce1b965c82edd59c435a84f13f --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c6c12d2ecda33ea4d917beafd3117e9d6969676bcbffa9d1163830bce3b791 +size 425192 diff --git a/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4d0061003b9b5efd755f0afe58e67ee4765da7bc --- /dev/null +++ b/eval/planbind_L0_none_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e636e666b4f728502e88832b856bc96750d0114411f1a273471671892503f91 +size 1127063 diff --git a/eval/planbind_L0_none_s1001/eval_info.json b/eval/planbind_L0_none_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f61b17c55cd903becbae187723579cfa0b5a0e8a --- /dev/null +++ b/eval/planbind_L0_none_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737663708, + 19.999357861210626, + 19.999261015106253, + 0.025646880467186772, + 19.999351096844578, + 19.999312915592547, + 19.99907880413695, + 19.99938108430215, + 20.000975007887504, + 0.2769336922240191, + 19.999412196099385, + 19.998557938997166, + 0.4579139414355522, + 20.000485722447788, + 19.999408076921227, + 19.999130387887917, + 19.999663696950613, + 19.99885127594629, + 19.99959164497252, + 19.998809129351322, + 19.99993176914441, + 19.998779729352506, + 19.99862159738705, + 19.99896791012983, + 19.999665853134747, + 0.16668325169588794, + 19.999375434985005, + 19.999619855408245, + 19.998922058852788, + 20.00056723370639, + 19.9988549922695, + 0.04585016160048794, + 19.999000967622603, + 19.999982291562993, + 20.00020002088764, + 19.99881655741657, + 19.999840292422974, + 0.30789568313725646, + 20.000772515823943, + 19.998879493593698, + 0.3088434848908186, + 19.999808951042397, + 19.99993255102848, + 20.000635763095104, + 19.999783656590658, + 19.998692358715857, + 19.999805654312567, + 19.99981869511626, + 19.998427932575275, + 19.999824841868985, + 19.999694909606905, + 19.99900067748193, + 19.999331146474088, + 19.999662883058804, + 20.000886584810466, + 19.998518485667503, + 19.998933500400454, + 19.999261489342583, + 19.999577234400057, + 20.000144784986283, + 19.999275931764544, + 19.99919864785869, + 19.999046207850263, + 20.000029539661956, + 19.999827464837526, + 19.99895406766362, + 20.00029944028509, + 19.99944871164918, + 19.99933807661133, + 19.999261797101013, + 19.999140619156712, + 19.999883984304486, + 19.99933542991961, + 19.999830033472158, + 20.00036871873388, + 19.999347294739334, + 0.4743198761531341, + 20.00095254059543, + 19.999424673641276, + 19.999724603880626, + 19.99952082058607, + 20.00104333534127, + 19.998596447223147, + 20.00028431355839, + 19.99885672390546, + 19.999208582694813, + 20.00124138742474, + 20.001107323354045, + 20.000325729089997, + 19.99905603221423, + 19.999070368460483, + 20.000344052484405, + 19.999901021249865, + 19.998787118277683, + 20.00051424668228, + 19.999249900740274, + 19.999326161966177, + 19.999296223871955, + 20.000535615620105, + 19.999456362726846 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 0.05042234868934359, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2038646478587582, + 10.0, + 10.0, + 1.3274626354372128, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.027460846711073517, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3855194101919024, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.03231587228744315, + 10.0, + 10.0, + 1.336249396935218, + 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, + 0.04685256645067071, + 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, + false, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + 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, + false, + 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_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": 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": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 95.0, + "pc_nested_middle": 92.0, + "pc_released_middle": 92.0, + "pc_picked_top": 92.0, + "pc_nested_top": 92.0, + "pc_released_top": 92.0 + }, + "n_episodes": 100, + "n_success": 92, + "pc_success": 92.0, + "pc_success_ci95": [ + 85.00189229905128, + 95.89065385156194 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.420254067893975, + "avg_max_reward": 9.254101477245616, + "pc_success": 92.0, + "n_episodes": 100, + "n_success": 92, + "pc_success_ci95": [ + 85.00189229905128, + 95.89065385156194 + ], + "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": 95.0, + "pc_nested_middle": 92.0, + "pc_released_middle": 92.0, + "pc_picked_top": 92.0, + "pc_nested_top": 92.0, + "pc_released_top": 92.0 + } + }, + "overall": { + "avg_sum_reward": 18.420254067893975, + "avg_max_reward": 9.254101477245616, + "pc_success": 92.0, + "n_episodes": 100, + "n_success": 92, + "pc_success_ci95": [ + 85.00189229905128, + 95.89065385156194 + ], + "eval_s": 1551.2694244384766, + "eval_ep_s": 15.512694249153137, + "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": 95.0, + "pc_nested_middle": 92.0, + "pc_released_middle": 92.0, + "pc_picked_top": 92.0, + "pc_nested_top": 92.0, + "pc_released_top": 92.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..60bbcc8fa63061f19906ea3dd37a943229ef3eae --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc12bbdcd5871480a3bd92abb5e2687408bc7ad8ade85dacfaaeec17290d1d0 +size 482035 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c96545c0864141542e4a4bd371851ed269a66afa --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c345b3be851fc42a7180ee782b65dd44b6d34bd15ad9534a755d95f2f5ae11a +size 435140 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..750b984f5646648fd24dc2d49cca6bcb0d4f7987 --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6114a3c5efccd607e91e9326c60f25ead5de62a2e917449179419eb56532f3 +size 522807 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ec897316ba63ae322b3fde7d2546b1552b89c1d --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd4129daea6e2ec1511188b548bb76881bfa6eebaabfb143abef97ff1635124 +size 1040471 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3ae1173693444260398dd79e02f9e19f1fe900aa --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87c6ba563771360b3b8ea8487f855e4b628c471a5d76862ea225111d068ade4 +size 509014 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bba163ff9801efe29a1c34f8ac7f5c209893bb6a --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48267bad58c202c54f3578ea0760c363f7c4f68d2f556509d1cf16ce956fc468 +size 481778 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ca26d17a76f897f516c05584d800564fccd55685 --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c433e250cab80800ce49f7d2dbbad1f86a61a5977ffb00e2970d9bfb7ec3d31 +size 487337 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..04ab8128d2c1e89ffb0f0ef47fd3bcbf882e7184 --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baa4c474f0242e5b1c76edb304204db7e010a1e16e9faf19a2e991c734ee7c6d +size 434824 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..613f4ad9c6bc5f26d82d2f00fdead79bdf4fafe1 --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ddcf068deb6f8995dee1eda4a9e8410566c6f14aed807ca6da6c18464b6717 +size 427592 diff --git a/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..33123952b00350411ac73bdfde914f04c7349bad --- /dev/null +++ b/eval/planbind_L0_none_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b587191a6e54c1425e70ad25d00f92cd420a469a330904525d74d7eed4db952 +size 887943 diff --git a/eval/planbind_L0_none_s1002/eval_info.json b/eval/planbind_L0_none_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..53893b887bfecc33ea15eb25bd268abc3ba68eec --- /dev/null +++ b/eval/planbind_L0_none_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999744608586234, + 19.999378169910123, + 19.999261005126904, + 19.999071268212475, + 19.999342195869396, + 19.99933450321364, + 19.998960604256602, + 19.999372694362933, + 20.000926697239315, + 19.999347792349536, + 19.999414080934645, + 19.99855993282103, + 20.00015974339602, + 20.000437222326013, + 19.99929530569687, + 9.998813395962756, + 19.999701735893623, + 0.23506856320697656, + 19.999578678308747, + 19.999456031919102, + 19.999905219585845, + 19.998493250340516, + 19.998630185454672, + 19.999150829999294, + 19.999665842611122, + 19.99994487121671, + 19.999375374649805, + 19.999719611911985, + 19.998804131560927, + 20.000675038968055, + 19.99884912811071, + 19.99952776932684, + 19.99901959944612, + 19.999929725527995, + 0.1974342763156971, + 19.998585489611024, + 19.99987771169959, + 20.000286644294576, + 20.000744094942313, + 19.99889134267947, + 19.999662182827034, + 19.999802675930383, + 19.999864967651945, + 20.000642878162886, + 19.999262958140825, + 19.998625434775825, + 19.99914217828817, + 19.99990438509507, + 20.000007749525217, + 19.99981057256081, + 0.23765790573998635, + 19.999063845627795, + 19.999331124195077, + 19.99950338219416, + 20.00091109481586, + 19.998567455664425, + 19.9988264766186, + 19.999261489342583, + 19.999608957588435, + 20.00006604333539, + 19.999275931764544, + 19.99919864785869, + 19.999053638236443, + 19.99993263770475, + 19.999797938515673, + 19.998962746274977, + 20.000395002406627, + 19.999465614183215, + 19.999484166822526, + 19.999261797101013, + 19.999140619156712, + 19.99988475963041, + 19.999329605942638, + 19.999815463960136, + 20.00030423837143, + 19.999347325744047, + 20.000575768853814, + 20.000994478397956, + 9.998842547616231, + 19.999745108213105, + 9.999062375139317, + 0.30536919092561265, + 19.998596072836605, + 20.000195783116002, + 19.999125034455375, + 19.99921726760482, + 20.001529213538902, + 19.999627560164413, + 19.998524442659477, + 19.999045702161265, + 19.99928995922993, + 0.13156658681784128, + 19.999901021249865, + 19.998837135316602, + 20.000492624018488, + 19.999758229220127, + 19.99926020373648, + 19.999378621097065, + 20.0008836159003, + 19.999497589939764 + ], + "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, + 4.753110081769774, + 10.0, + 0.02557195384227251, + 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, + 0.03140929260851122, + 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, + 0.03939480685777352, + 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, + 4.332469251872823, + 10.0, + 1.6306149140810051, + 1.2164059818830641, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.035795377159196784, + 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, + false, + true, + false, + 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, + 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, + false, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + 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": 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": 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": 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": 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": 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 + } + ], + "pc_picked_middle": 96.0, + "pc_nested_middle": 95.0, + "pc_released_middle": 95.0, + "pc_picked_top": 95.0, + "pc_nested_top": 95.0, + "pc_released_top": 95.0 + }, + "n_episodes": 100, + "n_success": 92, + "pc_success": 92.0, + "pc_success_ci95": [ + 85.00189229905128, + 95.89065385156194 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.710642243918095, + "avg_max_reward": 9.320647716600744, + "pc_success": 92.0, + "n_episodes": 100, + "n_success": 92, + "pc_success_ci95": [ + 85.00189229905128, + 95.89065385156194 + ], + "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": 96.0, + "pc_nested_middle": 95.0, + "pc_released_middle": 95.0, + "pc_picked_top": 95.0, + "pc_nested_top": 95.0, + "pc_released_top": 95.0 + } + }, + "overall": { + "avg_sum_reward": 18.710642243918095, + "avg_max_reward": 9.320647716600744, + "pc_success": 92.0, + "n_episodes": 100, + "n_success": 92, + "pc_success_ci95": [ + 85.00189229905128, + 95.89065385156194 + ], + "eval_s": 1403.2750198841095, + "eval_ep_s": 14.032750208377838, + "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": 96.0, + "pc_nested_middle": 95.0, + "pc_released_middle": 95.0, + "pc_picked_top": 95.0, + "pc_nested_top": 95.0, + "pc_released_top": 95.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ffe1f55b4246a6fac6f716d1df88f206c0bfa3ca --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d95a396cabfea0310c2666689d233593e1bfec5895d3704064a554dd0a229c +size 497789 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fdccd3231beb9085e9e8f3748e58285567fcd983 --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac10ea21f7859a8b7c3e6c85cb4674ded5281fd6d67d53f021e8c7475b8cc97b +size 439384 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8afa6f1b8c5e4a7a6c6e94d1f0a56f3ba9a61b00 --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d7aa24d8629ad8f529e5546020277ee8837ec55eb52189fee2615ba531da23 +size 483556 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7bfc699a2867e4ce6f097a2738f472b432f329fd --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f433bc7de4950c44480791ddb7d38cad28fc975b2d1e1f5aa478624eb70fbd8 +size 497866 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b9c01a9df3b1af3e1daa93e34e74d92a883c2c80 --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c94d56e305f87ba71c350a7c54389e315e4235f6ea674cb78fc24668a110e62f +size 502280 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a3ed54fbad868a088802e08f7dca976b1515de0b --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76714eb4629b623bb27fa06c917a30203a00ab76ad449ab40838b883d060ef45 +size 485078 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7f517d6aea45297a47ce81e4d591c3597b8094ba --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80e399aeb675e4690db1270f2dd06004c847591c6df6e62f4d166c29b2db74d +size 480810 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ec86b7ac48e7ed69562c510318a5b1259da2b7f5 --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0792ca8aa398435a175fc6e7a962b402410931c4c7c8922ba8c22f48ca2fdbd +size 448982 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..50e6afa4cf5237492523a7e6a2de9c65ad75622f --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b053573db1ce63b4b4a33770f451c96005b5fc39e6486bc0ed90b49cb40d079 +size 420402 diff --git a/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..13886af7bea8f43bb2f8f0d892fd070d1aa0d0e8 --- /dev/null +++ b/eval/planbind_L0_none_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b1b08a7a211273b6880eb79583ce2a0be059b195e0783110ea7814c22efa71 +size 432199 diff --git a/eval/planbind_L6_latency_s1000/eval_info.json b/eval/planbind_L6_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b2951835b876c8af256d90bc4b0fc4b857202de0 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232075, + 19.999353787655874, + 19.99926106877139, + 19.999188335092853, + 19.99925223241442, + 19.9992835935453, + 19.99909228438174, + 19.999422782718476, + 20.000964793406293, + 19.999360940066218, + 19.99945533926641, + 19.998559378272375, + 20.000100942046004, + 20.000421733771898, + 19.99940948734601, + 19.999029411134234, + 19.999693104285527, + 19.998849825490403, + 19.999530610292304, + 19.998809129351322, + 19.999971863380026, + 19.998779721426303, + 19.998608858447092, + 19.999148134629124, + 19.999665905834384, + 19.999743914224148, + 19.99937770626243, + 19.999779534014618, + 19.99880413156093, + 20.00081919333592, + 19.998854850039532, + 19.99947143168512, + 19.99902122335242, + 19.999987566401725, + 19.9988365188051, + 19.99881227269053, + 19.999859217880577, + 20.00036457190421, + 20.000709600075524, + 19.998858698221014, + 19.999544151888443, + 19.99981889923703, + 19.99988401954272, + 20.000752364604892, + 19.999837900302666, + 19.99865159583741, + 19.999142178288174, + 19.99983089004473, + 19.999949312756904, + 19.99981543670692, + 19.999652094614458, + 19.999063878820607, + 19.999331046581883, + 19.999570618748184, + 20.00090144182917, + 0.10620597443253543, + 19.998812608695424, + 19.99946970293069, + 19.999613047931383, + 20.000135977432393, + 19.999275931764544, + 19.99919755552035, + 19.99905293242177, + 20.00005340162238, + 19.999815143997186, + 19.998952194860106, + 20.000253662638883, + 19.999457277753326, + 19.99934910893522, + 19.999370348213528, + 19.999533607837442, + 19.9998951341837, + 19.99932975659138, + 19.999842069474354, + 20.000392306284606, + 19.999346570986766, + 20.000646702088947, + 20.000952621807, + 19.99884254761623, + 19.99978444908227, + 19.99945820885518, + 20.000864983722302, + 19.99859381536815, + 20.00023564344431, + 19.999081109122343, + 19.99921658440689, + 9.999027210194429, + 19.999605257541887, + 20.000366686198866, + 19.999045503020753, + 19.999290000939414, + 19.99911688437369, + 19.99990102166741, + 19.998789455224404, + 20.00047218961617, + 19.999649466449508, + 5.134708657529564, + 19.999296093155593, + 20.000935124012308, + 19.999479066009183 + ], + "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, + 1.2194648339136895, + 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, + 4.799513993835221, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.548909307358766, + 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, + 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, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_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": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": 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 + } + ], + "pc_picked_middle": 99.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 99.0, + "pc_picked_top": 98.0, + "pc_nested_top": 98.0, + "pc_released_top": 98.0 + }, + "n_episodes": 100, + "n_success": 97, + "pc_success": 97.0, + "pc_success_ci95": [ + 91.54806357094724, + 98.97454759759611 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.55198173793471, + "avg_max_reward": 9.775678881351077, + "pc_success": 97.0, + "n_episodes": 100, + "n_success": 97, + "pc_success_ci95": [ + 91.54806357094724, + 98.97454759759611 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 99.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 99.0, + "pc_picked_top": 98.0, + "pc_nested_top": 98.0, + "pc_released_top": 98.0 + } + }, + "overall": { + "avg_sum_reward": 19.55198173793471, + "avg_max_reward": 9.775678881351077, + "pc_success": 97.0, + "n_episodes": 100, + "n_success": 97, + "pc_success_ci95": [ + 91.54806357094724, + 98.97454759759611 + ], + "eval_s": 1313.011281967163, + "eval_ep_s": 13.130112824440003, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 99.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 99.0, + "pc_picked_top": 98.0, + "pc_nested_top": 98.0, + "pc_released_top": 98.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2ef2b08a3e0c5ad03aa59821565858fea2adfc51 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a1115b599a9a8ee3badbab3aa7e1fbb60f477021a3ed16e8168ddac6419067 +size 505673 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0363dfbd7f89106a6f385711fdbaf8fccbfef16c --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b94a33aa7c3836e9810365b60faa59b85a8b906804259c91cbb4accb830d0bb +size 424574 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..733859f2f0e1efc105540ae61f5070a87868a8e9 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59004140aeb384e524d210a93af0209c5b16cb36ab57482b0b4149fe5aef0ae8 +size 489610 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1b51668042444a1789857298e2a8efcdaa5d7545 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ff6ebf1ad067c24c4b32f21ba16362896798258e42d969097bf1e51a00d25e +size 485904 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f59013dcce4719dd2705ff070699a3675391c822 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b156a0ac1d3193a3e31bc77d138c440abc98c0842a12b60aba4f94478882b9 +size 467438 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..829a2f8b937addae9b81c7c4aa67559c7a2b71c0 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967ee0ee99c85bda4a86f75af54afedabbb91e9f66265f325ccc58df2633d9f4 +size 486507 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..78259cd1e67d7106a521262def14e44ce1b08a1b --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94583554c6c77fda162e62051c1a946fd611aef0dc2de4a70e870efe8a5a3698 +size 473454 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..451161386d1cf9a5a56ac35065ea62f887375f89 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc179cbc2954c0c74b95921c23eb6f7ec1e11c0ecdcc0b126fa87873c827b22 +size 419309 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5504a92ed97120a661c2c03749dcc35f48202eb4 --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfaed4444ce21a828e88b1610e8610db3e402763380003f842b28a9c0ffc814 +size 411780 diff --git a/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..387b88466c547f9d8e17a09f32cfb6a6e0f5f40c --- /dev/null +++ b/eval/planbind_L6_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15623fbb1a3d66172836f35a9993a9fad3b2ca8f192bcba98e58f08bf8f24c57 +size 438414 diff --git a/eval/planbind_L6_latency_s1001/eval_info.json b/eval/planbind_L6_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..a02164ed9fc18280e6f4b1c7edf3b5bd8d555b90 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.99935925009042, + 19.99926110930496, + 19.99918615982088, + 19.999133165286576, + 19.999063347077005, + 19.999094798330216, + 19.999377816367435, + 20.000998205202222, + 19.999353420269948, + 19.999446715791077, + 19.998557666460137, + 19.998774778236793, + 20.000480046153413, + 19.999410666293024, + 19.99903535067456, + 19.99969004803551, + 19.998847708525577, + 19.999514958666467, + 19.998809129351322, + 19.999975404928, + 19.99877966136681, + 19.9986535149164, + 19.998967910129828, + 19.999665869773985, + 19.999786891797847, + 19.99937761214026, + 19.99974936884724, + 19.99880413156093, + 20.000650743564094, + 19.998848983532916, + 19.999459645402304, + 19.999023966245954, + 20.000017736368456, + 19.9988365188051, + 19.998805407045843, + 19.999278899879666, + 20.000402697706157, + 20.000726832564755, + 19.998875677647757, + 19.999592400772222, + 19.99981895510585, + 19.999943840866987, + 20.000767906826752, + 19.999262958140825, + 19.998639576728294, + 19.999142178288174, + 19.999821239095986, + 20.000005526066097, + 19.999901501889024, + 19.9996617613121, + 19.99906389578241, + 19.9992428663852, + 19.999619363246516, + 20.00100931979764, + 19.998539444992375, + 19.998829708249453, + 19.999471537481412, + 19.999181003971284, + 20.0001366024369, + 19.999680032192366, + 19.99919785684431, + 19.998874948681163, + 20.000041839642975, + 19.999818363887506, + 19.99896227197961, + 20.000365976624764, + 19.99944610494481, + 19.999348684101598, + 19.99926179710101, + 19.9995373939907, + 19.99991619452716, + 19.999154890342137, + 19.999842511607415, + 20.00038124157994, + 19.999346474601882, + 20.000660905330562, + 20.001006849471615, + 19.99884254761623, + 19.999726515018157, + 19.999464192195614, + 20.000861957487004, + 19.99859845774223, + 20.000261286185687, + 19.99885672390546, + 19.99921635704828, + 20.001508801225363, + 19.999564404707378, + 20.000361216627148, + 19.999056032214227, + 19.999070368460483, + 19.999112974090387, + 19.99990104327183, + 19.998797697517926, + 20.00053776300081, + 19.999614263364037, + 19.99926020373648, + 19.999303476346274, + 20.000855962656566, + 19.999452842763354 + ], + "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": [ + "/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": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 19.999540035004614, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 100, + "n_success": 100, + "pc_success_ci95": [ + 96.30065017930143, + 100.0 + ], + "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": 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": 19.999540035004614, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 100, + "n_success": 100, + "pc_success_ci95": [ + 96.30065017930143, + 100.0 + ], + "eval_s": 1058.5439116954803, + "eval_ep_s": 10.585439121723175, + "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": 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/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b1adcc3d6355739c4bc98eb790b8be9362f01177 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c2f8faf0c63498e2703bd9c90b96d6cba56f7125e6891abd29e81e5f9d4640 +size 500588 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6d94a128b45c3ae1727c8d49550aa256a854cca6 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c08aaa297ae6777bd26f95f7c93de0e459f5d49214b02dd6d77f4840f441d1 +size 427707 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..deb4df6950cf4fba9e1e7edcd8dc6eb002ffbc6d --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f0b9d9927ac00943311bb804685478743e3470321fcd6384d31c86fe6d3dfc +size 489217 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..82d7989f4d9ceb71b34945eb3158ed4e59f88edd --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f2100219ab7a07b7286f0bb7bd93d0b7c5396f105cce07943ce04793abd4d2 +size 490382 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..eab16a87208fe0cd9a051577d49b65f44aea922a --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5847ad2ae2fcd3fc9f27e4a66d778a6d235258c2ce6a611760f7529bcf74d3da +size 472437 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..676a9c82055e7384f6d459338974d5fe2f548db3 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b442e531901c9329218a944e259fdfda06c7cdd4558df8da4fafda6033b530f4 +size 490630 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d87441aed061f53221ebd1937d744407f349d623 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50bc451c50a1d3311c5c9184d82b5f6c4f6a2907040270a37d833597af350ab0 +size 487027 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ba2eb4f01657de427a18c13a35980be78228b310 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4beb22fe89d1cb7ba07302d2083692759b8a2e3bacebde462f21a2848b54c09d +size 430014 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9a3d00c2c55c5744c0fb2f1396399c58ce3bf3f9 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cbaf5ecd497ca03f91ee5111723940d39e157c2a6e5bf956042bfb7c40819b +size 419822 diff --git a/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..38bf58bd96e8fbd20021ff742ff3d6880d258830 --- /dev/null +++ b/eval/planbind_L6_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f5905cea0c0157a09e30c62ee302afbda91ac9ae8aee615c0548837685c768 +size 432916 diff --git a/eval/planbind_L6_latency_s1002/eval_info.json b/eval/planbind_L6_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..c73ea5685bd306c1ab7ccc1402bf5e08c62f3e89 --- /dev/null +++ b/eval/planbind_L6_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 19.9993726889066, + 19.999261030061312, + 19.999187949101277, + 19.999276887842452, + 19.999322862978403, + 19.99910572238172, + 19.999424596661765, + 20.000963440548855, + 19.998891811677485, + 19.999433788978138, + 19.998558940976725, + 20.00013723891007, + 20.00046520179928, + 19.999295305696872, + 19.99905490639761, + 19.999684652253954, + 19.99886876529056, + 19.999541237021667, + 19.998809129351326, + 19.99998062516814, + 19.998779754063495, + 19.998658110430018, + 19.999149004164398, + 19.99921522030574, + 19.999806379768465, + 19.999377008524952, + 19.999790113545835, + 19.998804131560927, + 20.000687333841256, + 19.99882462665304, + 19.999478011479038, + 19.999021546576024, + 20.000061516823667, + 19.9988365188051, + 19.99858548961103, + 19.999878571305622, + 20.00034395629563, + 20.000769055119466, + 19.99879493932982, + 19.99962445039043, + 19.99981873135037, + 19.9999871561666, + 20.00077367620745, + 19.999262958140825, + 19.998656336737636, + 19.99914217828817, + 19.999824438449764, + 20.00002705179509, + 19.999838310925888, + 19.999700537981884, + 19.99906377500827, + 19.9992428663852, + 19.999618109791907, + 20.000873592010045, + 19.998552976320198, + 19.998861926067864, + 19.999482065787628, + 19.99918100397128, + 20.000139676643418, + 19.999275931764544, + 19.99919728923964, + 19.999051194128256, + 20.000050536220414, + 19.999805860821223, + 19.998964980259053, + 20.00031030438976, + 19.999456427088962, + 19.999338921096392, + 19.999261797101013, + 19.999573397763996, + 19.999977629058495, + 19.999154890342137, + 19.999838464602945, + 20.00039946240546, + 19.999347400477603, + 5.136117517257217, + 20.00093321035628, + 19.999423389921265, + 19.99975761334605, + 19.999435849503925, + 20.000923760491066, + 19.998599345009502, + 20.000266381691045, + 19.99885672390546, + 19.999227011436442, + 5.166242115160586, + 19.99958123546851, + 20.000358049247374, + 19.999046040569887, + 19.999289995993802, + 19.999118774375887, + 19.999275900800882, + 19.998801795172753, + 20.00050300183222, + 19.99964017501913, + 19.999260203736483, + 19.99930379156755, + 20.000886019698903, + 19.999499009636324 + ], + "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, + 1.559840640184864, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 9.78488748212559, + 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, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 99.0, + "pc_released_top": 99.0 + }, + "n_episodes": 100, + "n_success": 98, + "pc_success": 98.0, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.70255721960818, + "avg_max_reward": 9.913447281223105, + "pc_success": 98.0, + "n_episodes": 100, + "n_success": 98, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ], + "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": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } + }, + "overall": { + "avg_sum_reward": 19.70255721960818, + "avg_max_reward": 9.913447281223105, + "pc_success": 98.0, + "n_episodes": 100, + "n_success": 98, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ], + "eval_s": 1212.1301045417786, + "eval_ep_s": 12.121301054954529, + "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": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..34db439c3e42f0fda20194e3a241d7ee4fcc26ed --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:031de6bd1e683d8dd886a006c26f05ba3525a430551c7db8291725417fcf63b5 +size 503949 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3bcb19614c688bd6c25259a27c529666aedcd9d3 --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba22e8274c56334a3c1f411ef354f434d2767d44804ba13551d508e0335b8ea8 +size 434366 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d7056a1b880806149947f3ff297099462690b5ee --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dacf94285274e98b1722b845e1f3da1718102e13a2304c86ce0e3066dadca8e4 +size 490687 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..502e82b97c2558f1252a326bc0fd542988a68c03 --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b4278b59b372eee38e32d31f062ae9b6db2530bb74bf017e9053f25d1468c5 +size 478313 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..076b306e7be61d3165058fa9b98fcf201486e08b --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19c2268e0617306ccdbf79e95076d6cbf0704e2054ae11669cc6ec318237193 +size 473386 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d7203b287a01dc49cd611bd72adc1b1ccf7b5e3b --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1792d7d702dfd5dd41f96f5de95cdd1aafe7ae87ae1ca238efee8fa7f29cb963 +size 485240 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..826687e1cdabbf3d4cb3a65a13fc89f26073da6b --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232c79ceb9eb7a3ca3b4a2c7bf5bfc123d370c60d37492888ead12c8b44cf210 +size 481885 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..02ca6b9874cbbef4adc804a9817ab69a397b8f2b --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86e5ed703ada3e807aa4dbaee20efe4d3193edc4454d348d3dbe73bbc2279dcb +size 435078 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bba45afc587533b7b337c66172ad07e27146ea76 --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74f52283d4d1da13f4711e8464be01511343164701922d38da894eb61949825 +size 431712 diff --git a/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..90c1966321b7713877a7b6099933403542149b56 --- /dev/null +++ b/eval/planbind_L6_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb086e176e773e1277f64a0f842be393fbcfa14ed7350f19f0389caef6710f9 +size 636377 diff --git a/eval/planbind_L9_latency_s1000/eval_info.json b/eval/planbind_L9_latency_s1000/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..c9945aaa5b350b313d343252bee6bdf309d71d41 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 19.999355616407076, + 19.99926100081747, + 19.99918745158864, + 19.999251711088014, + 19.999063347077005, + 19.999102599711193, + 19.999378568900777, + 20.001032946981002, + 19.999344726014826, + 19.999290942134582, + 19.998558950200664, + 20.000211375502456, + 20.000449227334933, + 19.999408185513893, + 19.99903552784692, + 19.999684162671727, + 19.998839508860595, + 19.99951736861219, + 19.998809129351322, + 19.999919194148163, + 19.998779671256642, + 19.99861513300549, + 19.999150602703818, + 19.999215220305736, + 19.99977594615829, + 19.999377709157123, + 19.999830810575205, + 19.99880413156093, + 20.000677008867402, + 19.9988448337662, + 19.99879684881501, + 19.998991005036938, + 20.000033415987065, + 20.000357511738905, + 19.998585489611028, + 19.99984362104449, + 20.000343348645973, + 20.000700928155492, + 19.998868646540135, + 19.999577145494555, + 19.999813516534765, + 19.999938707774174, + 20.00083008246008, + 19.99926295814083, + 19.99864105341769, + 19.999142178288174, + 19.999818234794507, + 20.00000925590207, + 19.999871406407102, + 19.999688871960053, + 19.999064007721177, + 19.999242866385202, + 19.999608417990558, + 20.000888017409363, + 19.998547775832826, + 19.99878771049208, + 19.999261489342587, + 19.99960744328111, + 20.00014093099039, + 19.999275931764544, + 19.999197293606578, + 19.999046169012686, + 20.000018620870843, + 19.999800026774555, + 19.998954886223956, + 20.000284289167595, + 19.9994549814165, + 19.999306919197892, + 19.99926179710101, + 19.999492140847536, + 19.999924997979782, + 19.999154890342137, + 19.999851651924594, + 20.000348276904056, + 19.99914650615869, + 20.000661722697753, + 20.000880996396457, + 19.999423404874953, + 19.99977734132234, + 19.999462501893476, + 20.0010066875292, + 19.99860441829292, + 20.000202004836293, + 19.99885672390546, + 19.999082143516688, + 20.001511425066823, + 19.999604770843376, + 20.000366079448487, + 19.999045560551266, + 19.999290032583385, + 19.99912869864098, + 19.999275900800882, + 19.99880008455814, + 20.000454224878304, + 19.99962965292644, + 19.9993321330773, + 0.4867622511366575, + 20.00091707677721, + 19.999467487012836 + ], + "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, + 1.3591040245506303, + 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, + false, + true, + true + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_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": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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 + } + ], + "pc_picked_middle": 100.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 99.0, + "pc_picked_top": 99.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + }, + "n_episodes": 100, + "n_success": 99, + "pc_success": 99.0, + "pc_success_ci95": [ + 94.55138038212947, + 99.82325679358593 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.804432988714073, + "avg_max_reward": 9.913591040245507, + "pc_success": 99.0, + "n_episodes": 100, + "n_success": 99, + "pc_success_ci95": [ + 94.55138038212947, + 99.82325679358593 + ], + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 100.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 99.0, + "pc_picked_top": 99.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } + }, + "overall": { + "avg_sum_reward": 19.804432988714073, + "avg_max_reward": 9.913591040245507, + "pc_success": 99.0, + "n_episodes": 100, + "n_success": 99, + "pc_success_ci95": [ + 94.55138038212947, + 99.82325679358593 + ], + "eval_s": 991.9825491905212, + "eval_ep_s": 9.91982549905777, + "video_paths": [ + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4", + "experiments/261029-plan-bind-d1b-seeds/outputs/full/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 100.0, + "pc_nested_middle": 99.0, + "pc_released_middle": 99.0, + "pc_picked_top": 99.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e9eafa8b79efffe44d68750ceabb084c6a5769c6 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29fd311684a682489ac3839c94318d18894b62e68f27f7609134fea0e2c9e2f5 +size 504833 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8368bc8439000b7d371682be7d6d1541dd0fa446 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c352ca849598c6bcc858f4c77d7034230100a6c40f4ce34066947296bb2e077c +size 421317 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0792cfd028d2f551be660d6ea0de06db3545c2ae --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5bcd65ee09b005468951ebbb03ed4369b8a9db66a0639aab3e827c5f1397f4 +size 485451 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bf85c184e6b61a8abae5c04030fac35be1263003 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a1e0c328c506a17c32117e78965966cbe261886b487c37defb37c1cea5226e5 +size 494161 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..642f37866145dca3858bf64664a49da370e09646 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70263ccb9db20f416ed1af0a13cee94962b856fd89899e99e4e6ce7f18dc6425 +size 477737 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8178a8a1582385be26c11119d2104fc8ebbcb98f --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1020fe96dc35041e7cf9746b8622090d5bfb2205a1ccca562c66a03415dfbd79 +size 478981 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..146213fce8dc93a2e7a0a9dd17e9d108f6cbd18d --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90dbcab5a1e70d7b00dff93e58e3d058726ce1d7994b1238d7673c36a9038603 +size 463671 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7502c13d3c188108e86cab265fe28f5784b63578 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0ad7732a2b3d48dbbc023f4a6ca0962d1e8bc12d07370b8272a23c48566e51 +size 448358 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0223990f4fc4a1e9550c5205a2c4abb3042393d3 --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be020a8b7686b9ead38716f8fbe055933dbbcfef60a35c69c5266cc81fe91649 +size 433876 diff --git a/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7d723e5aae63fb292b5e852c198a31fd4c70039b --- /dev/null +++ b/eval/planbind_L9_latency_s1000/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7742896a324e621a1692116d01aff91551fa7eac22f42defa008d894b63c6359 +size 435330 diff --git a/eval/planbind_L9_latency_s1001/eval_info.json b/eval/planbind_L9_latency_s1001/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5945fb7cf54bd90aad8d11145aadeb2a1ff1e82d --- /dev/null +++ b/eval/planbind_L9_latency_s1001/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741716433654, + 19.999351993886776, + 19.999261109523232, + 19.99907126821248, + 19.99923217275552, + 19.999063347077005, + 19.99909685024602, + 19.999404506007796, + 20.001001060951296, + 19.999353301434404, + 19.999290942134582, + 19.998559594772146, + 20.000167267979833, + 20.000413046891943, + 19.999404605779763, + 0.3033940725810842, + 19.99969183002938, + 19.998854700944882, + 19.99947132796734, + 19.99945603967693, + 19.999981639722638, + 19.998779776865895, + 19.998616417451156, + 19.999150393223616, + 19.99921522030574, + 19.999759668042593, + 0.0672508420655733, + 19.999828659712634, + 19.99892403595728, + 20.00060513888284, + 19.998837798714128, + 19.999459434854312, + 19.999012928902367, + 20.000039617894892, + 19.9988365188051, + 19.998822714294025, + 19.999278899879666, + 20.00034810331629, + 20.00077428596533, + 19.99885830441164, + 19.999606306090108, + 19.999817525255555, + 19.999929540500478, + 20.000664209321748, + 19.99926295814083, + 19.998613252230484, + 19.999142178288174, + 19.999836463432697, + 20.000020779367347, + 19.99985276267321, + 19.998823564518418, + 19.999063776092573, + 19.9993307152706, + 19.99958466989824, + 20.00099540715198, + 19.998531147535463, + 19.998784170294652, + 19.999471439698382, + 19.999181003971284, + 20.00010719263894, + 19.999275931764544, + 19.99919833429994, + 19.99904433136048, + 19.999979136029364, + 19.999821088447433, + 19.998946569826877, + 20.00023930930207, + 19.999448395092507, + 19.99932239522972, + 19.99926179710101, + 19.999140619156712, + 19.999853724138195, + 19.99932962320124, + 19.999834209922934, + 20.00040327600422, + 19.999146506158695, + 20.000729700586657, + 20.001064710100657, + 19.999422581622536, + 19.999744364956634, + 19.99943761111838, + 20.000943011220553, + 19.998604020744327, + 20.00027162368883, + 19.99885672390546, + 19.999214647949394, + 20.001552791481316, + 19.999537270557624, + 19.998524442659477, + 19.999045001898708, + 19.99907036846048, + 19.999111381338018, + 19.999901089062423, + 19.998793076113543, + 20.00057446057834, + 0.12893863276343065, + 19.999326970698437, + 19.9992615354695, + 20.000868600441844, + 19.999462367200127 + ], + "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, + 1.6165972128610417, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.321861435645837, + 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, + 1.3919569014398416, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + 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, + 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, + 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 + ], + "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": 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": 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 + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": 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 + } + ], + "pc_picked_middle": 99.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 97.0, + "pc_released_top": 97.0 + }, + "n_episodes": 100, + "n_success": 97, + "pc_success": 97.0, + "pc_success_ci95": [ + 91.54806357094724, + 98.97454759759611 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.404547824485775, + "avg_max_reward": 9.743304155499466, + "pc_success": 97.0, + "n_episodes": 100, + "n_success": 97, + "pc_success_ci95": [ + 91.54806357094724, + 98.97454759759611 + ], + "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": 99.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 97.0, + "pc_released_top": 97.0 + } + }, + "overall": { + "avg_sum_reward": 19.404547824485775, + "avg_max_reward": 9.743304155499466, + "pc_success": 97.0, + "n_episodes": 100, + "n_success": 97, + "pc_success_ci95": [ + 91.54806357094724, + 98.97454759759611 + ], + "eval_s": 1209.5686197280884, + "eval_ep_s": 12.095686204433441, + "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": 99.0, + "pc_nested_middle": 97.0, + "pc_released_middle": 97.0, + "pc_picked_top": 97.0, + "pc_nested_top": 97.0, + "pc_released_top": 97.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d645f92064c5b19b3a505b8157db51c2e408d69d --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ee102b99adecbe47d69b3274cc52a11bdf57b5b93622317987a992114cb5b7 +size 489739 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f751f892bbe1f1530d768c42f309e26e25198f65 --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2271f0a9feee649e6661976a40ae02e5a2a6f44d2071d61da6901153c3b564 +size 449431 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d2e0424d59fe8c824b981696a150412a891b57f0 --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5533537f198b0dec9bc1dfe3b8d51aa0b70ee32d64d6929eb887076984d916 +size 490826 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e9bcc32ea04a915499c7db47ca428f1fc50a08d1 --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a6f4d5511426cfb898fdc378a65d9687af554b85b9bad048a4e4afc777a63a +size 491817 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f75d942f015d2eddb4c390d86fd93a97fe72f06a --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa545bc51b083ed6c057650614dcb8be829043237e61b83243e90e429a47b15c +size 477663 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..59be45f3f350b38a1012e472cc4d5190236fd16a --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b3c8aa40f47577e490b98b136d355cef5cc46d04d993877d531ee1178294ce +size 494489 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b8345427a7115f3b8b2c3f8742ec58ebb6073f0f --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b6bdc3d13c48dc6be65063f7984e494d413463b0aebc66b9c99431a69c22cb +size 478521 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7664041e4a0f52a58e979aacd7045b2350c09cc1 --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a5ffcce45657bb614f78140b047bc3606e302cdf5fdc415e81b9ff9f3d640b +size 433130 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b347830df68b2d9ecee6570cb2a50a8131b659c8 --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a316d917df5b6a5c6a93da88da1b401bca80171a99a9542b1636ad5b37e826f4 +size 419795 diff --git a/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a0a5879a2b5a03dcfe86edd39eb9f56499651132 --- /dev/null +++ b/eval/planbind_L9_latency_s1001/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0aae6434c223db75ff1e9f7dfe803df62f9ace8f68e592ecf4403eff1210117 +size 444216 diff --git a/eval/planbind_L9_latency_s1002/eval_info.json b/eval/planbind_L9_latency_s1002/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f0345702a0ab418d3ea2d479b5785b24cac6fa30 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/eval_info.json @@ -0,0 +1,1208 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.999359410925955, + 19.999260995789665, + 19.99918616758788, + 19.99918204691392, + 19.999063347077005, + 19.999110624870774, + 19.999384236625954, + 20.001023055644946, + 19.999348165003244, + 19.999290942134582, + 19.99856694957364, + 20.000166690718533, + 20.000470617642705, + 19.999409915785378, + 19.999042457975968, + 19.99969518221026, + 19.998851234275463, + 19.99953401085797, + 19.998809129351322, + 19.99995250901447, + 19.99877968548497, + 19.998646045043262, + 19.999150829999298, + 19.99921522030574, + 19.999766045232956, + 19.999377718615023, + 19.998683241697425, + 19.998924088158212, + 20.00075558744752, + 19.998814789649067, + 19.999469558235894, + 19.998996437407975, + 19.999989606070187, + 19.9988365188051, + 19.998585489611024, + 19.9998597916209, + 20.000357785166347, + 20.000706548161517, + 19.998878322811166, + 19.999645560866846, + 19.999814827700522, + 19.999920964492908, + 20.00082324953715, + 19.99926295814083, + 19.998639832222164, + 19.999142178288174, + 19.999838124515087, + 20.000036697424633, + 19.999854262991345, + 19.998823564518414, + 19.999063807065937, + 19.9992428663852, + 19.99958740971671, + 20.000946594381816, + 19.998549765701043, + 19.998837889284907, + 19.99945670409954, + 19.99918100397128, + 20.00013674271558, + 19.99927593176454, + 19.999197183215106, + 19.999052887397394, + 20.000045637034102, + 19.999811156365272, + 19.998958098230922, + 20.000396315752113, + 19.999449815749884, + 19.999364586630993, + 19.999261797101013, + 19.999499935767624, + 19.999814827567413, + 19.999329635137844, + 5.564266734907491, + 20.00040430181316, + 19.999146506158695, + 20.000649414008087, + 20.000951975445044, + 19.99942308717569, + 19.999721806723727, + 19.999450520432717, + 20.000985756505013, + 19.998598396229742, + 20.000262039023724, + 19.998856723905458, + 19.999226512897533, + 9.999027210194429, + 19.999556945414678, + 20.000348843699772, + 19.999045857766262, + 19.99929003258338, + 19.999118722871383, + 19.99990103176553, + 19.99878843112738, + 19.998317320410038, + 19.999597962514052, + 19.99926020373648, + 19.999323079453823, + 20.00090993984275, + 19.99946786635125 + ], + "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, + 1.6252462943288242, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.6354675193194765, + 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, + false, + 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 + ], + "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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": 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": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 99.0, + "pc_released_top": 99.0 + }, + "n_episodes": 100, + "n_success": 98, + "pc_success": 98.0, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.75513861708427, + "avg_max_reward": 9.832607138136483, + "pc_success": 98.0, + "n_episodes": 100, + "n_success": 98, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ], + "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": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } + }, + "overall": { + "avg_sum_reward": 19.75513861708427, + "avg_max_reward": 9.832607138136483, + "pc_success": 98.0, + "n_episodes": 100, + "n_success": 98, + "pc_success_ci95": [ + 92.9988209271456, + 99.44980324498376 + ], + "eval_s": 1268.401920557022, + "eval_ep_s": 12.684019212722779, + "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": 100.0, + "pc_nested_middle": 100.0, + "pc_released_middle": 100.0, + "pc_picked_top": 100.0, + "pc_nested_top": 99.0, + "pc_released_top": 99.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1f3e06a1c024aac7e1b5613640e7daabb5fb9f00 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eaf9ab6afe73154e8668ae46fc61add8856b9d6e23f855ce6e36e556fa3a997 +size 498134 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9a10c500f286bf4dc47b2fbd9a9361596f714039 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9816dfa58046c0c6f025b58bede2c218e277e9c37e3eae2947ce470557fa2e56 +size 432149 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b1fc1310c26bc7f8214762e134cce2edc7d186cb --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7f106b01f6bc700ab037c0df02dfdfaa39bf4e550dcc65db153903872fa0e7 +size 487097 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1aeb9accd4b24a406a0da9db5e9f49c12b08905a --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9062f34e78e60d66ec0c2ecf129499db20c16c49016e72a9dd05de9bf649f7a2 +size 486438 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f7b5e5273f296df1aa4f1e85c220f430cf45ad35 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18edee591838f325342080480a7051f300b7c2a197cbc563aaf0277f71c0e115 +size 469570 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0d7af38e84ba773b86ffd23d9c2a55107cba3f53 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edffadb366fa497aec4cec0fc0af806ba25a5f30dadedd079fd7acb86a0a6804 +size 490475 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..48ffc0376fd251623e6218befe59eed88556b325 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff00439add014164074fb5b3b26eefba89dad1fe4c546d3d4840778435a31717 +size 481115 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4ee3bc65b62692633f96d8d2bb3a48431a9f9860 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c684b4d041d87cbb564df6c1eb2eafd2275e1b40709acbeacab9cf681e83a7b +size 426394 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5b30dd05d067d462b31a34f66462fb66bbedb076 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f141112b583c5f66172a860e9ced442751e204e6f611892559952ca21e9119c +size 414932 diff --git a/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d199305faff25f4dc89ffba4d2c735efe7624cd4 --- /dev/null +++ b/eval/planbind_L9_latency_s1002/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063648bad0c72e5b73f9797bbaadd8ae682a3e2b9e1d1d867eae06cae64074c3 +size 433095