diff --git a/.gitattributes b/.gitattributes index 5b736a72ad42a2d9130356b13679d09560b5bdd1..a58203d0b390552f64c67e76dffe3365e3aa0e89 100644 --- a/.gitattributes +++ b/.gitattributes @@ -260,3 +260,166 @@ eval/onestep_L6_now/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge eval/onestep_L6_now/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text eval/onestep_L6_now/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text eval/onestep_L6_now/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_now/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_now/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/onestep_L6_now/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L0_now/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L2_latency/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L5_latency/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_none/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_0.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4 filter=lfs diff=lfs merge=lfs -text +eval/planbind_L6_now/videos/nexarm_0/eval_episode_9.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/eval/onestep_L6_now/videos/nexarm_0/eval_episode_7.mp4 b/eval/onestep_L6_now/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..43dea7abd2c91fa7d5ffed9bf70ab6554dac436e --- /dev/null +++ b/eval/onestep_L6_now/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74494d922372094fc31660a03d4333b16b79d8167698f20799b1b8b4f4e06db9 +size 447099 diff --git a/eval/onestep_L6_now/videos/nexarm_0/eval_episode_8.mp4 b/eval/onestep_L6_now/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..095a4cb5241bb601adeda0037a47337c75570172 --- /dev/null +++ b/eval/onestep_L6_now/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626fb35f9e57dda88398025e002d1054883988f3e6a8c80355da36f8ef7dbbc6 +size 409859 diff --git a/eval/onestep_L6_now/videos/nexarm_0/eval_episode_9.mp4 b/eval/onestep_L6_now/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f2c836e2c4cb16f464eb675b0ef04c5ed57960cd --- /dev/null +++ b/eval/onestep_L6_now/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c059eaeccbc232eecf678c2bdd5d3c736b9183f2391b0367f13e585afd7bd6 +size 565628 diff --git a/eval/planbind_L0_latency/eval_info.json b/eval/planbind_L0_latency/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..4cbe1706b2e68de81188749e5b40ffbcbb717481 --- /dev/null +++ b/eval/planbind_L0_latency/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974172941686, + 19.999361957517646, + 0.09529052628987866, + 19.999188637931343, + 19.999270608643606, + 19.9992777478245, + 19.999105284953263, + 19.999418590257783, + 20.000916084683926, + 19.99934790335388, + 19.999441898509225, + 19.99855993369729, + 20.000135085231243, + 20.00036255548894, + 19.99929530569687, + 19.99901467169276, + 19.99965857824038, + 19.998859509067078, + 19.999555595867243, + 19.9994569103765, + 19.99985531412613, + 19.998779777987995, + 0.10474769178772037, + 19.9991507777862, + 19.999665855566953, + 19.99976391548153, + 19.99937519088873, + 19.999789464676386, + 19.99892399145604, + 20.00058700809152, + 19.99888170004406, + 0.038407886172903805, + 19.999002096083213, + 0.3174886601296423, + 20.000375268562795, + 19.99882321007272, + 19.999868311628127, + 20.000463377952194, + 20.000718933888276, + 19.998874396568954, + 19.99966454912113, + 19.999821159472905, + 19.99832065039298, + 20.000663036384665, + 19.99991149341564, + 19.998641353576787, + 19.999142178288174, + 19.999830717745947, + 19.999877647273827, + 19.99981914113524 + ], + "max_rewards": [ + 10.0, + 10.0, + 1.114471630191873, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.0249885570106535, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.035302288875288856, + 10.0, + 1.3545529658928146, + 10.0, + 10.0, + 10.0, + 10.0, + 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, + false, + 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, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 94.0, + "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": 50, + "n_success": 46, + "pc_success": 92.0, + "pc_success_ci95": [ + 81.16175308165717, + 96.84504859114071 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.410689877409993, + "avg_max_reward": 9.250586308839413, + "pc_success": 92.0, + "n_episodes": 50, + "n_success": 46, + "pc_success_ci95": [ + 81.16175308165717, + 96.84504859114071 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 94.0, + "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": 18.410689877409993, + "avg_max_reward": 9.250586308839413, + "pc_success": 92.0, + "n_episodes": 50, + "n_success": 46, + "pc_success_ci95": [ + 81.16175308165717, + 96.84504859114071 + ], + "eval_s": 316.0980794429779, + "eval_ep_s": 6.321961598396301, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 94.0, + "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_latency/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c24783a368fbc325328860e18beb326de917c8c6 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7f4db59fd908cce005394dfe0fa203ddbdbe8bf271fae2af6c531fb67bfc58 +size 489326 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d8edec52b1e147f6070f3f740040e5a4379ca32e --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc0d49351a079adbb951fc8c5284624810720fa0510c56577c742eda45e1b421 +size 407913 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8d974b16d8aa8ffcc1d753d271b86a53ac66bd84 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d9a66bad7f1c73735b9bdb1404c4267ffc2897b67b17298d795947145a84db +size 817669 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..927b5babe73265d2d18e473b7c3a59a01e4b8f3b --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d30579a36a09191cfc30a39b78d821871a6b4010c91eae20a384b5b2e3af63d +size 500260 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..80df587209bc7f1c02370e1e10c13cefc30fa5c0 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb6c4a995100a6b956489e561576cf2da87ca5f96c5d3b73998d294ccf4409a +size 462500 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ba6a5c0809c8104d2b4753c1b94317f98857e41 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3e81641acc39558a8928d9bcacaea52be0dce74088f4a8bb814f886d284ce8 +size 471801 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..154a0c6a749dd79d99c7013bc1943a7b9eaa3c14 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70e96033d54e44ec0f573bd289d1a9985beb053b137bca08d47165d23ab6f3d +size 472312 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e6703fed65fbb0a026f3dc552006540340cccecd --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49fdb4bdbc60b33c14ece09bfc10a840e3003a8fa1dbb2eaba906582e62e07eb +size 426478 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b64072432256fd92da88f9170a5a1632c59511c0 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ec0d4175b06be3747df7465b19ea60bd5f8e7475461c5036d8be731c4227bb +size 428448 diff --git a/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..425d5950207eca13b5992d5716bd3462380503e8 --- /dev/null +++ b/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0d0df872978103756ae4814ea8905a25fc5d00118087293026ed6ea3187a2b +size 453891 diff --git a/eval/planbind_L0_latency_every12/eval_info.json b/eval/planbind_L0_latency_every12/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3f97ae4e034136d71e06759db7834a358278ee07 --- /dev/null +++ b/eval/planbind_L0_latency_every12/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741737174134, + 19.999391859412178, + 19.999263753522907, + 19.999071268212482, + 19.999261028431466, + 19.999302371272123, + 19.99910521737052, + 19.99936728425638, + 20.00087407023826, + 19.99934810189884, + 19.9994400163422, + 19.998566739307286, + 20.000226780388815, + 0.5047509365408563, + 19.999432414262188, + 19.99900804119921, + 19.99969578723319, + 19.998862872175632, + 19.99954329370221, + 19.999456952159278, + 19.999923670860593, + 19.99877966161788, + 19.998621052273588, + 19.999150744034768, + 19.99966585289271, + 19.99978001569758, + 19.999378372784253, + 19.999753858425862, + 19.998804131560927, + 20.000660360868906, + 19.998847965297372, + 19.99879684881501, + 19.999019029717978, + 20.000059679976065, + 20.000297574795297, + 19.998817169586754, + 19.99986922186341, + 20.000450500115367, + 20.000663647220307, + 19.99892625433735, + 19.999655563134063, + 19.999822593932475, + 19.999992350831697, + 20.000613738103535, + 19.99984059479896, + 19.99861367685864, + 19.999142178288174, + 19.999835100159313, + 19.999943501183278, + 19.999810653928566 + ], + "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, + 1.342928236281642, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 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, + 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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/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": 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 + } + ], + "pc_picked_middle": 98.0, + "pc_nested_middle": 98.0, + "pc_released_middle": 98.0, + "pc_picked_top": 98.0, + "pc_nested_top": 98.0, + "pc_released_top": 98.0 + }, + "n_episodes": 50, + "n_success": 49, + "pc_success": 98.0, + "pc_success_ci95": [ + 89.50455641036218, + 99.64607407283539 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.609624921781215, + "avg_max_reward": 9.826858564725633, + "pc_success": 98.0, + "n_episodes": 50, + "n_success": 49, + "pc_success_ci95": [ + 89.50455641036218, + 99.64607407283539 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 98.0, + "pc_released_middle": 98.0, + "pc_picked_top": 98.0, + "pc_nested_top": 98.0, + "pc_released_top": 98.0 + } + }, + "overall": { + "avg_sum_reward": 19.609624921781215, + "avg_max_reward": 9.826858564725633, + "pc_success": 98.0, + "n_episodes": 50, + "n_success": 49, + "pc_success_ci95": [ + 89.50455641036218, + 99.64607407283539 + ], + "eval_s": 242.11361622810364, + "eval_ep_s": 4.842272324562073, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "pc_nested_middle": 98.0, + "pc_released_middle": 98.0, + "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_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4c7ed4ef5352f6543efd8b917a473f503e7308d1 --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95fb344d9fe85abb2995fed0d51617cca131b3140be8363a8f7294c5d142b296 +size 488657 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a24b1b6dc7e590aa1825606a89fa9639d091e513 --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be09558883a401ae884790c498b93190d3abdc6392799dca19da78813e964a1a +size 420355 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2882084abc5014f4c35cc43ffa63b5d7e38b630d --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ab55b8c282bd5fbd0e968a82ab8fb07970ee49bed59ff2ea06ce7bac4555da +size 499473 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..625ce55fe825da6992fe2366274a1f8ab229d80b --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e500f3d977b1d14382e1e6a5ad0756e2fab8d737e993224b9bfbea344b8375 +size 500632 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..90b19d3e68d77e9e4848b938bb4c0d68be94b1c8 --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4712b0f98fd25e8a70321392feabc3740f599b01998efd89c74e6b503d16fe7 +size 462929 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bcc9703bf90c400869af2e118f8ad80a7f4f5fbb --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ceb54e9a9315da2eee2f2f1cf7e1d1c2cefd39af93f18103e727619e33b6e8 +size 463114 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5f0ad834b4cae10018852af6f35258d5683ce9e6 --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2292d260b0e2be48d36de3310a205055383d9fd16e9946508c9d15e20ed7cc +size 476636 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..29b23e747beb60cb653b26694f859919dd96d373 --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:689b3ebddc8bb3f9bd0d67dd4d15c0bb929c072c50acbde7b71ed2ab501ec6d8 +size 437601 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e170770ca5bc3d53d77947a2c1a630262078c25e --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4ee8ab56c34cda2b262be6fa70e7369ce87b5e712202ffd54adb91923396721 +size 413583 diff --git a/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4cdcd441b465694d257f672a00bf00d0bf5ea4f9 --- /dev/null +++ b/eval/planbind_L0_latency_every12/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b018a75a92b0775a043ca99a2df914ebd5544ddd3b85d641396742e2f89506 +size 448263 diff --git a/eval/planbind_L0_latency_every8/eval_info.json b/eval/planbind_L0_latency_every8/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f6683eacc12ad5efce85fa02a97a4be382eda7e0 --- /dev/null +++ b/eval/planbind_L0_latency_every8/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 19.999373692982807, + 19.999264360542327, + 19.99918786478102, + 19.999262864314318, + 19.99932131131206, + 19.99909742281526, + 19.999397157148, + 20.0009337170896, + 19.999352253528627, + 19.999420146971808, + 19.998560532004586, + 20.000204672175897, + 20.00046079919619, + 19.99941876661101, + 19.999028770028062, + 19.999650272144862, + 19.998840228817265, + 19.999544999371842, + 19.998809129351322, + 19.999964490366487, + 19.9987796537509, + 19.998640211667194, + 19.99896791012983, + 19.999665854277854, + 19.99973827957775, + 19.999375038645834, + 19.999780973516618, + 19.998923258079216, + 20.00064987512495, + 19.99886388638524, + 19.999460755206574, + 19.99899964673859, + 19.99994466820468, + 20.00027113999336, + 19.998817273135295, + 19.99927889987967, + 20.000227718863222, + 20.000690598102178, + 19.998841841488492, + 19.999642601350704, + 19.999802675237696, + 19.99982635794626, + 20.000658773560545, + 19.999262958140825, + 19.99858755034477, + 19.99979364921051, + 19.99982481463287, + 20.000017190634132, + 19.999842899791272 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.999509421588048, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/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": 19.999509421588048, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 211.47508096694946, + "eval_ep_s": 4.229501628875733, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_every8/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_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..abcab7f7a0a128fbff076d49199ccd750ca1f59a --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17177cd1d58c9be50813f63f37399d12e31eb4187cd73cd22a463c5f29f73a61 +size 510663 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c91e8a4afd6ac02f53e548714005736053a4f0ce --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb570d153d9d45cfbf7db46a116c5d8081692f3e463ff135d514cf4bf1575bf +size 425109 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e44b4c618d23a535eea353a097c48b98263ad794 --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928c4987f4f4ed85be3edf020d06ae85fc51995fefbaad6d5ca00363934e1302 +size 502440 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f738a76c7d89939ffb0a91f39c5a0e2c73796b2f --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ad03a2bb16d4462ec004e99ad6d577e50475943d399a531cd6b80d3e161af0 +size 488767 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8e709ac47a6d22f1bafc53997c352955383957a1 --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a3b3e411becb13c69f0338722f9e712f9b9c1aaef972abb5793048e80533f3 +size 459799 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5360167a2680b629dc6d821e35da3d73beae211f --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53fbe145a4716cf7c8ad8e46d9b944fdadb5a43bdae3f3fc611639ee11050335 +size 482646 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..54af6ea8b56ce3699806898081c01f567bee0272 --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383736c336d72b5bbf6fe4020977e561bb12dea314826aa279787436cf53c9d9 +size 474135 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b06be18cdc20c803395b6b186c169c22dd5b985c --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd372de9c96cb40e88f4c2051448f6e706a7b735eaeaeb0f4330567ed9a8862d +size 435900 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2227d94b13068efe018ddcd177aa2ba61031eebb --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1213285088d92e204d5fd13dccc3145ede096543cf653ebed4969157c91124 +size 416303 diff --git a/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e80a6165f297781556005e230a697894d5be1142 --- /dev/null +++ b/eval/planbind_L0_latency_every8/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e452ea2c6692f4151eb3b58981847dab21324e3c737546a3b84c3110a383aa2f +size 448065 diff --git a/eval/planbind_L0_latency_shift3cm/eval_info.json b/eval/planbind_L0_latency_shift3cm/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5ca7ee7d9f757b490e5be03b5789c94ac67886d0 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999751023808813, + 19.999424156904997, + 0.08777481369685591, + 9.999071268212479, + 19.998998130812303, + 9.999063347077009, + 19.999086028154508, + 19.999422709802374, + 20.000612825119887, + 19.999352712871158, + 19.99940943428573, + 5.1238378609388455, + 20.000132919651215, + 9.998768270132953, + 5.483028138680614, + 19.999036111512318, + 0.23116349533261837, + 9.998702880590324, + 19.999390559238574, + 9.998809129351319, + 19.999818619590364, + 19.998779630790725, + 19.998869753028927, + 9.998967910129831, + 19.999665839034755, + 19.999672490977375, + 19.999374343819387, + 9.998683241697423, + 19.99892392539266, + 20.000808782599666, + 19.998765390263543, + 19.999480312797616, + 19.999180504969537, + 0.2543853001638039, + 20.000504967151286, + 19.99879584926217, + 19.999611535947786, + 20.00059061849219, + 20.00090087253563, + 19.9986421248369, + 19.999610063437913, + 19.999833304787458, + 20.00004116212001, + 20.000946270516074, + 20.000176823091152, + 19.99855495499165, + 9.999142178288174, + 19.999797038046992, + 19.999760858888262, + 19.999860110659345 + ], + "max_rewards": [ + 10.0, + 10.0, + 1.1160121363285627, + 1.5650913068192205, + 10.0, + 4.87586343173257, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.7267790396468565, + 10.0, + 1.625333225845274, + 8.597851453167383, + 10.0, + 0.04562996166332467, + 1.6758910009873138, + 10.0, + 8.497347467276317, + 10.0, + 10.0, + 10.0, + 4.917903893580773, + 10.0, + 10.0, + 10.0, + 8.573480465597024, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3608397126411822, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 4.698557756877287, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + false, + false, + true, + false, + true, + true, + true, + true, + true, + false, + true, + false, + false, + true, + false, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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 + } + ], + "pc_picked_middle": 96.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 94.0, + "pc_nested_top": 92.0, + "pc_released_top": 92.0 + }, + "n_episodes": 50, + "n_success": 37, + "pc_success": 74.0, + "pc_success_ci95": [ + 60.44684273515117, + 84.12847250644762 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 16.62313961188967, + "avg_max_reward": 8.385531617043261, + "pc_success": 74.0, + "n_episodes": 50, + "n_success": 37, + "pc_success_ci95": [ + 60.44684273515117, + 84.12847250644762 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 96.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 94.0, + "pc_nested_top": 92.0, + "pc_released_top": 92.0 + } + }, + "overall": { + "avg_sum_reward": 16.62313961188967, + "avg_max_reward": 8.385531617043261, + "pc_success": 74.0, + "n_episodes": 50, + "n_success": 37, + "pc_success_ci95": [ + 60.44684273515117, + 84.12847250644762 + ], + "eval_s": 383.79956459999084, + "eval_ep_s": 7.67599130153656, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 96.0, + "pc_nested_middle": 94.0, + "pc_released_middle": 94.0, + "pc_picked_top": 94.0, + "pc_nested_top": 92.0, + "pc_released_top": 92.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d9c1d301d7aaa2ab828349ed1ad0eb3f278235eb --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82a6fe79f4c2df1e78a620b18b80757fa9ee5152402e1bf3e4ffd74d5e31f6f0 +size 468627 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7b106dfbc7a38fc43889bd2edbe42fae4e04d721 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6013bf71c16cb73bb10e053926bdfcd4c12fa47b2d236887a538b6787f7bcd45 +size 449736 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f9182d9d15cb14b0e92fd1061d6ee23e2a3bb8da --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5a0913028ac6d441d401f5bdccfed7ef7f5906fbace6125a1b762e4f006599 +size 840341 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c9606b8373060faa30177901261ae83ed23c65b1 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5742e169db6b3ff2d79f452145b658cc958286da2734b7b833d0b8b091fb80 +size 949206 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2a5c28267b08a159d256b535ff708128626912d0 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e5f3baa6eb1c9d224704566ba015d4cb6f5d26d99b9ae15cc4d04ebebf6c88 +size 494448 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1b6b6418712295d3cda5b0ffb4442f0124de3a98 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e868cf96c66c0b52145122235bab495e2866f0a79c2e723186266c170c82f93f +size 987371 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..04af4e48c5fe673116a9ca1e924a6cb089dedfa4 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c03cdadbcfda91ee158b48027ca0a13edb47eec8ab1293095e7b162b6ea482 +size 504429 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..da087d6f952a1f392b247f236fd3f178bb342209 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd527a05cbc94939e608c8d5bab599655874a6ebe94dd142279491abc0aec109 +size 425972 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8453366da426224cd7f87b994bd4ccf0599babc1 --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f220328491cdd7e903ac82505c0d7685f8c218d8a90bc6b23e7252dc385b0a13 +size 434820 diff --git a/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ff3e4da612f88e0006817762a2c3245a74fbd1da --- /dev/null +++ b/eval/planbind_L0_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e368631dc4a75c1336c58ee75c685969b4e6e888bf767fb477e3081aee024b8 +size 471028 diff --git a/eval/planbind_L0_none/eval_info.json b/eval/planbind_L0_none/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0327d463c673132bc0cf1483967b9bcb5c7072d6 --- /dev/null +++ b/eval/planbind_L0_none/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741732082292, + 19.9993749535682, + 0.06517700312502606, + 19.99918795441979, + 19.999354785835855, + 19.999305042391867, + 19.99909444219284, + 19.999436107739697, + 20.00095343345978, + 19.999353066623705, + 19.99943955503608, + 19.99858888041281, + 0.3067627018883404, + 0.47690094443258346, + 19.999417557086495, + 19.999019444517383, + 19.99967162477491, + 19.99886806614837, + 19.99954142102483, + 19.99945694381435, + 19.99985162186975, + 19.998493250340513, + 19.998624170770473, + 19.999152790034874, + 19.999665839034755, + 19.999831809627494, + 19.99937823709292, + 19.999756012829824, + 19.99892343164552, + 20.000706207496105, + 19.998840280959566, + 19.999456002190986, + 19.99900940590086, + 20.000036151128796, + 20.00020383920245, + 19.998818211190137, + 0.06005205916227785, + 20.0002179365243, + 0.23741693254659801, + 19.998953935165947, + 19.99967361350237, + 19.999820768445836, + 19.999807071330597, + 0.19664303896830715, + 19.99983531862073, + 19.999608240975867, + 19.999810022688152, + 19.99983114472411, + 19.999972144703797, + 19.999817461781358 + ], + "max_rewards": [ + 10.0, + 10.0, + 0.029326789678992937, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.02948354137911824, + 0.039734686012591, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.5702163283493002, + 10.0, + 0.027526364659749558, + 10.0, + 10.0, + 10.0, + 10.0, + 0.038515615317530116, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/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": 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": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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 + } + ], + "pc_picked_middle": 90.0, + "pc_nested_middle": 90.0, + "pc_released_middle": 88.0, + "pc_picked_top": 88.0, + "pc_nested_top": 88.0, + "pc_released_top": 88.0 + }, + "n_episodes": 50, + "n_success": 44, + "pc_success": 88.0, + "pc_success_ci95": [ + 76.19518261679701, + 94.38239984906772 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 17.62641705222061, + "avg_max_reward": 8.834696066507945, + "pc_success": 88.0, + "n_episodes": 50, + "n_success": 44, + "pc_success_ci95": [ + 76.19518261679701, + 94.38239984906772 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 90.0, + "pc_nested_middle": 90.0, + "pc_released_middle": 88.0, + "pc_picked_top": 88.0, + "pc_nested_top": 88.0, + "pc_released_top": 88.0 + } + }, + "overall": { + "avg_sum_reward": 17.62641705222061, + "avg_max_reward": 8.834696066507945, + "pc_success": 88.0, + "n_episodes": 50, + "n_success": 44, + "pc_success_ci95": [ + 76.19518261679701, + 94.38239984906772 + ], + "eval_s": 359.3926601409912, + "eval_ep_s": 7.1878532123565675, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 90.0, + "pc_nested_middle": 90.0, + "pc_released_middle": 88.0, + "pc_picked_top": 88.0, + "pc_nested_top": 88.0, + "pc_released_top": 88.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e1ecd216ff1b3b0e58a48c48162a54875fb2b856 --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729d9124aa13737170eaa6b38b8c035973849e12731bd778b83d09b3679b527e +size 520409 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6175303a4259b0530ccf18bda1438eebea1ca05d --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2ba83950c3081eef69d69a7e28053d2b5923b3a8618521cc2e0cb2d59ef5f5 +size 426403 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2f69e4c355d188cc560d86af6967c24c282dbb85 --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f085b50cece0c9cf260c9b0513a573bd903cde2877ee995dd76712ed205683dd +size 824664 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bc456d0bbd158b1a1f8154ced6cc26211fe82a79 --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185cc0148d4186cd1f5d048b9aba4cb8cda60e3527df65f0f7f7a24ed414900d +size 498731 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..80a714295a531d65684e931bba6f77fa8872a43b --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21dc077c8902b4ab3d80672963cd2225f755d3076196b94bd2e0a9a75254a87d +size 471549 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7f1e6ff84899111b637d413b4c3fb2e1268d12d5 --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c996ae92fa43141ca7e6f6c3f1633de8ccb9d36ad108f0861d1f9a674643cb +size 467719 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4db20243602b7be140d380d35624e9e0e1187c22 --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d48f69ca60614fb7eff2508a9b695e066cbb2a4fd31a0fe41cf001113a3487f +size 470241 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e74b009428166259b7194864a6f0092c72beba0f --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b58f190168c68d881adffc2c837d115643d948ccd3ef8a63dc5a210a8f3b3c +size 436772 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2d8d8924feaee5f57fa6d90428c80113e213987b --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0740d21297be0c3ebf19a68618bf84caabd4196c3629e4ca1a64f0931e014ee8 +size 429203 diff --git a/eval/planbind_L0_none/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e589a27725c7375e242a7c6d6a275f1c0d79bbe6 --- /dev/null +++ b/eval/planbind_L0_none/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8a4f5bf29d8cd2fa2c37f8b92e16fae7d3abf6440aa9926c4bda3ae67a564f +size 469199 diff --git a/eval/planbind_L0_none_every12/eval_info.json b/eval/planbind_L0_none_every12/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..038d59ddec802f53884ab329708d8db9d78b648b --- /dev/null +++ b/eval/planbind_L0_none_every12/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.999369886234135, + 19.99926099578967, + 20.000081126184032, + 19.99928110256385, + 19.99930992585632, + 19.9990972910451, + 19.99936961735156, + 20.000909302816158, + 19.999347385874817, + 19.999412300597417, + 19.998563966808543, + 20.00012852565214, + 20.000383536146487, + 19.999424195025775, + 19.998971468835904, + 19.999659755674088, + 19.998857507902404, + 19.999542603424516, + 19.998809129351322, + 19.999971749622198, + 19.998493250340516, + 19.998620713599518, + 19.999150746526304, + 19.999665839034755, + 19.99974619931265, + 19.999378407420647, + 19.999694441253563, + 19.998924166880442, + 20.000592346032054, + 19.998836058577407, + 20.00117212580638, + 19.999001967110708, + 19.999954358065626, + 20.000256182435216, + 19.998585489611024, + 19.999788067011526, + 20.00031342182561, + 20.000649256451027, + 19.998868264937038, + 19.999660102775426, + 19.9997992209001, + 19.9998926826476, + 20.000744187708868, + 20.001029153437166, + 19.998615206851703, + 19.999142178288174, + 19.999822913215162, + 20.00002250295301, + 19.999815838005844 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.99958374672007, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/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": 19.99958374672007, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 208.2226161956787, + "eval_ep_s": 4.164452333450317, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every12/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_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3480f3e238f00ecd717523d77dd6574c06c0691f --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4577c2204408f8a7e9d77e62acf9edf3cfe75f802da4aa80bc01b135bf40941b +size 518033 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8b3eb217d16847c2e15a648da2d91f539e8aed43 --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c912944b592a7a2a211163dea1e65fc25b9eac8781f10ab9469d8ec2f0bdd4 +size 427532 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..49ab4b89b5a0285b0e80c73147b24ba58cbee1ef --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1c9857f6641844a3adef664635cd768a3a518a85c8d3d27b2ead3e191533e7 +size 506788 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0610c638524ce74e410ca1dc497462a81331233a --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2e0cbf138b0dc89c69b22f381efda39b354d517991742052b13383b31d49b10 +size 499718 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..514ae20801dd2b4d8376628e53e72f46ec3f1191 --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de8a413114a4ccba4597850fccf081f91711aae70d126d29213d0e50cfcae88f +size 469175 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..85697b892e586d9e7f1a818a6f4c7722499d7cac --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfe86cbf65627d97e50f89b4808a83ff341e8a16a36af3473322ae235018850 +size 472930 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4c961a46545a0146629eb2248be7c5de40347c49 --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa02e6d98a7ec0d16d28378f40d9befa3d644bbb6243ec01c0de89a338a61015 +size 479282 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3fba889b3747988b5b6c6ab9bd0fa619231bbd50 --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f25517b77d1379503e1bf57b02f3847d9e278fdb5d5f56ad2658407dc51615 +size 434825 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ee449ba8310ca5279a1a7a61799df24b0b99c836 --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25346a7b5696bff0826cdf20baebbb899c160668c166c300cbd3227a5430c970 +size 417352 diff --git a/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c22ba4f61a9048f9aff207a1bfa7d8ff0a4816f5 --- /dev/null +++ b/eval/planbind_L0_none_every12/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efe842ab571576025f56dd1b052263ee678dd7697f296b422896d4ce367ecf8 +size 457571 diff --git a/eval/planbind_L0_none_every8/eval_info.json b/eval/planbind_L0_none_every8/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b6a595b4ce12c1e40303216c9ba0575dbae0df --- /dev/null +++ b/eval/planbind_L0_none_every8/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974172959346, + 19.999371073485378, + 19.99926340788578, + 5.639960494746818, + 19.999241018261205, + 19.999301739394742, + 19.99909837995745, + 19.999419414430506, + 20.000949858234133, + 19.9993489896855, + 19.999469789391302, + 19.998560017893116, + 20.000134820162096, + 20.000444997798816, + 19.999424090345222, + 19.999033625559925, + 19.999655483579254, + 19.998857659297357, + 19.99954864128432, + 19.998809129351322, + 19.999968349316852, + 19.99877961301656, + 19.998690576589155, + 19.999158880567506, + 19.99921522030574, + 19.999748664669916, + 19.999377338288166, + 19.999861561960067, + 19.99892411610484, + 20.00055355537026, + 19.998854809686353, + 19.99947931396508, + 19.999000453126456, + 19.99999925061011, + 20.000188433975097, + 19.99881598662862, + 19.99927889987967, + 20.000234846679795, + 20.000699572687957, + 19.998867585207563, + 19.99968568359148, + 19.99979445872253, + 19.999912269471757, + 20.000592396533957, + 19.99926295814083, + 19.998620002860346, + 19.999793917242823, + 19.999821265998897, + 19.999887813417647, + 19.999800344456435 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 1.5246270936597988, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 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, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + 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/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "stages": [ + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "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": 98.0, + "pc_released_top": 98.0 + }, + "n_episodes": 50, + "n_success": 49, + "pc_success": 98.0, + "pc_success_ci95": [ + 89.50455641036218, + 99.64607407283539 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.712330049988203, + "avg_max_reward": 9.830492541873195, + "pc_success": 98.0, + "n_episodes": 50, + "n_success": 49, + "pc_success_ci95": [ + 89.50455641036218, + 99.64607407283539 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/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": 98.0, + "pc_released_top": 98.0 + } + }, + "overall": { + "avg_sum_reward": 19.712330049988203, + "avg_max_reward": 9.830492541873195, + "pc_success": 98.0, + "n_episodes": 50, + "n_success": 49, + "pc_success_ci95": [ + 89.50455641036218, + 99.64607407283539 + ], + "eval_s": 235.92864155769348, + "eval_ep_s": 4.718572840690613, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_none_every8/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": 98.0, + "pc_released_top": 98.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ead0e9d31c59e6e6d8430a49858f6b2c11a37466 --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41318f7a305be314cbc54a561dd8b1ecb893eba1658bc330b12061f880071fb9 +size 501243 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..bf78132a1398a9048922d51fe274230fa21ce8db --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6352865544ed96a20289444272576e12961de2626764f5d1a90bf807b2d8071d +size 424323 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2adf29ac8c661733103a7a9088db2701961d5ac0 --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fd8bf54f72d8cb0d915c44f47550b2ae2ece7dd89d5cb3880eddfb60f95c38 +size 497701 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9616a821f1b3d0d8bdb3615e2321e67bccb7df55 --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a914685ab4405d44a08999a6c51a24cc210c878bba2b04f2b5b8e1b8e0fe81dc +size 1025140 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2ffdb3d1699ba225c6e3a6bf678c6d986ac2ddad --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda6b2a993573859cf84269f0ff2eb146a345cd9b36a151b6237cfeb84004ed0 +size 458943 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..95e356992ed2c31bd05f549f3313b4eac8f8f9a4 --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ee7392cd5b9134e0a0757bd43615cae94dffefad7f5db80af9bbbe59b0e974 +size 485684 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..282e45a6d1d1cfb95454b8efe470d224558b811e --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59c08eed7aee2d34ae7e4fa60abc1d98ca4960c6cd62f15ed1040e5fbb4e406 +size 478520 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..53848e0e41a8ab21daab4fd6e184ff50cd229464 --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38e3c6f5f12f21bf241b264f2eb08646c6334200496c61021cbe186d3365d4c +size 433429 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5c3c2761e1c0770aa9ce0155648749eea02917fe --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e010df91a4fa46e46440553447bd225f7f975e151ed91a99555a2a880888e1b +size 419186 diff --git a/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..88e316d5b1ea335aae753735a2bf5a3e8a60c9a2 --- /dev/null +++ b/eval/planbind_L0_none_every8/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4620add73a0689b054687ae8d1e149f0ed58c1cc500fc2039518a728be06ea1 +size 452172 diff --git a/eval/planbind_L0_now/eval_info.json b/eval/planbind_L0_now/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..805c067bc8a1bfe2e102fc92f3db6f37a859153c --- /dev/null +++ b/eval/planbind_L0_now/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974173204233, + 19.999368754405914, + 0.0691452542581159, + 19.99919227305865, + 19.99926691660191, + 19.999352807925654, + 19.999097929410578, + 19.999437636920913, + 20.00082271336317, + 19.99935060569124, + 19.999423211772303, + 19.998559775004345, + 20.000136314215492, + 20.000396700094605, + 19.999415554506545, + 19.998953329951107, + 19.999637228677525, + 19.998851881750948, + 19.999545452640817, + 19.998809129351322, + 19.99985988435705, + 19.998779718751702, + 19.99862320437755, + 19.999150798318396, + 19.999665887592183, + 19.99974970752827, + 19.999377473744552, + 19.99978547295716, + 19.99880413156093, + 20.000564456427583, + 19.998862524575706, + 0.03820681271296611, + 19.99900273916976, + 0.324904845952818, + 20.000232941189687, + 19.998813261883647, + 19.99985219635503, + 20.000320678380696, + 20.000741770513454, + 19.99887426522286, + 19.99966691290502, + 19.999807344536848, + 19.99985710508558, + 20.000679585582, + 19.99985898636109, + 19.998634344315604, + 19.999142178288174, + 19.99983741913241, + 19.999898886591893, + 19.999810294404995 + ], + "max_rewards": [ + 10.0, + 10.0, + 1.1150920133001794, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 0.03536902608888626, + 10.0, + 1.3610141180816426, + 10.0, + 10.0, + 10.0, + 10.0, + 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, + 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, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/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": 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": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 94.0, + "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": 50, + "n_success": 47, + "pc_success": 94.0, + "pc_success_ci95": [ + 83.78290831116182, + 97.9385029651026 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.80819742060838, + "avg_max_reward": 9.450229503149414, + "pc_success": 94.0, + "n_episodes": 50, + "n_success": 47, + "pc_success_ci95": [ + 83.78290831116182, + 97.9385029651026 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 94.0, + "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": 18.80819742060838, + "avg_max_reward": 9.450229503149414, + "pc_success": 94.0, + "n_episodes": 50, + "n_success": 47, + "pc_success_ci95": [ + 83.78290831116182, + 97.9385029651026 + ], + "eval_s": 278.23571038246155, + "eval_ep_s": 5.564714226722717, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L0_now/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 94.0, + "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_now/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0f786655c6f38867bfbd6fd709178c6d85d28aa1 --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcdc20a25427aba9131c9bcf19fdaaf619c0c0c430e2e0b6b8d845edf3b589e3 +size 489739 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9eb39ee73cd0354cfe926209fd3af168e62eddd6 --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29dd81817de2abdeef42ac4a47adbae5165dc978b5ddc461265befce2005291 +size 418687 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..95f5a5adb02772fe345976da222673e21ebf675d --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc0f4377e2aefe615b5402625bb61f3caf599babd309bcf198a4a98c89ae860 +size 813338 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5d9dc80a9f158407bd45270ea94434d9e4027a60 --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e8c5219c8ef949a9b048632331c623011bc6e24c330de132c4f43d0dbbcc58 +size 507767 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8422a415f86e263fdef0904f2be88f3a86de5bc1 --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d558a369d09b91a7b4efd7a9c4df16d827c1e2df141788981bb2c871f613e6 +size 467033 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7c6137560ae18c7705b4d1ec7dc5ae3f35373eee --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7762cb13f872dddc80061e4dbfe61a2d45fa3fda132a963e7a5b2d0ecd9a22 +size 472594 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e9b87e8cc7ae6b2eddae14adc17beb12b672f3ab --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb68d8492e9320d9d9ef407b99549076fb3d543b35f4deaa4ab9a4ad49197fb +size 475584 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6de957f6f671064a5cacdfbe539ade36e9497c91 --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a5727d69d4961ebc46898f7807846d6afa20a9fa95c65658ca99d2511f0eb0 +size 433460 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e1f2f0520ae4f4aeab49c132a861ae0a8d94f473 --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810366d6860ceadabe633b800c1e3c013fbb59f9641d842f5ee466c5d9f87fc9 +size 428759 diff --git a/eval/planbind_L0_now/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..89bf0018aac6b0a26ff258c9291786b2e801249b --- /dev/null +++ b/eval/planbind_L0_now/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39521efe11ac9678ea3c4c3c7ec6bea33668ff264a08d3359f2ec9e1ac40e55f +size 455476 diff --git a/eval/planbind_L2_latency/eval_info.json b/eval/planbind_L2_latency/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..63ea3f2c6f9ac7f005f567f0597c59a2e3affa52 --- /dev/null +++ b/eval/planbind_L2_latency/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741716633483, + 19.999366087651307, + 19.999261055208372, + 19.99918615748567, + 19.99926106894222, + 19.999307466024394, + 19.999096355777432, + 0.7693533980502816, + 20.000863187466862, + 19.99934936709865, + 19.99944108593625, + 19.99856007588208, + 20.00017796898776, + 20.00042339445523, + 19.999295305696872, + 19.99904242564355, + 19.999689294755992, + 19.99886260924719, + 19.999546916053298, + 19.999456876422872, + 19.999924439043493, + 19.99877970862658, + 19.998579898016672, + 19.99915075448179, + 19.999665842332234, + 19.999737997521915, + 19.999378816649532, + 19.999775430904492, + 19.998804131560927, + 20.000703476474904, + 19.9988442124975, + 19.999464518674, + 19.99901821737559, + 20.00001930970651, + 20.000251363066752, + 0.09087912962420597, + 19.999830665012958, + 20.00034272648107, + 20.000624219691428, + 19.998879058982297, + 19.99965698134612, + 19.99981464777978, + 19.99985390551592, + 0.2208730752881295, + 19.999912697083285, + 19.998614152159742, + 19.999797862603646, + 19.999842278304932, + 19.999957644081647, + 19.999820519348358 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.332492856404473, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.172131322049306, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2585649672235526, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + 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, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/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": 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": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + } + ], + "pc_picked_middle": 98.0, + "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": 50, + "n_success": 47, + "pc_success": 94.0, + "pc_success_ci95": [ + 83.78290831116182, + 97.9385029651026 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.821201589873123, + "avg_max_reward": 9.475263782913547, + "pc_success": 94.0, + "n_episodes": 50, + "n_success": 47, + "pc_success_ci95": [ + 83.78290831116182, + 97.9385029651026 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "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": 18.821201589873123, + "avg_max_reward": 9.475263782913547, + "pc_success": 94.0, + "n_episodes": 50, + "n_success": 47, + "pc_success_ci95": [ + 83.78290831116182, + 97.9385029651026 + ], + "eval_s": 318.71765971183777, + "eval_ep_s": 6.374353199005127, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 98.0, + "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_L2_latency/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..595c83fff7b6409f3381aa1deb003ae77dd5af32 --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cdc180f3aa1e1d6a967375d33c588131483378a5dd91e9fe88067fb46330df +size 498297 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b1ea3622e0b18967bf84c04403d7910b7014087a --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff2da4d92f28d4ad2925b4345f44a499276d3ce2ce734fcc149bc6850afebba0 +size 428610 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..86cbb0430f792f76c673d9c75303b59ae8dd1b9c --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c12fc1a9972a0c65cdc9021f781fc99cbd20347e0467e872714ad99a3fafc28 +size 494532 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ca70d066a8303656402f6d2c8a65424c3c6d5be --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db4b4ad362d859cb2b6ef04c7f6fac2b40a44f6ca362940f7569121cb88f5b7 +size 473923 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ab894d49fdb924cbdab0a6ee0252b3ceab51a06f --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a41a42bbd02189981763bad6f9e69f9945bae2b3aa964ae3fabb9adff46ac4 +size 464129 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..dbedab5de2b98919a04fc7a88f735fdf7ea888c1 --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41adef2e2d14ef41415c9ba43f7e2f35c5daf2ec927eb4bd283ec4e1fa1e20e +size 467363 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..14feb5b7e2dbe455c311d2bb8312bc17a4438c59 --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7a52df694545a6a49d073ada3da03ebb55f72586728a187f84940112121fee +size 467872 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7fa8949c75d17336cbc58619f02231c197c1cb75 --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a367cd4dc58b4c3c73796c139dd5b63557f828925cb1f71771303bf6aac2dfb1 +size 931644 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7b017a4b1b8e9d96d103ae88f1d89e78402ee89c --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae42e65af66981e21e9c58cf359197cade5246bda95e2582d266bd1070d4ccf +size 413758 diff --git a/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5a368128fe1919a82cd13df516c31fe92854c2eb --- /dev/null +++ b/eval/planbind_L2_latency/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a51061e20095a567e19d12a5c7123516a7e54f5c45f39d183e5d93a7bc3279 +size 448778 diff --git a/eval/planbind_L5_latency/eval_info.json b/eval/planbind_L5_latency/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b5d315092d53607ed318f432048957fb6f788775 --- /dev/null +++ b/eval/planbind_L5_latency/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999200674232068, + 19.999373924603248, + 19.99926778325349, + 19.999186174585937, + 19.999282512561805, + 19.99932120413826, + 19.999104335204287, + 19.99941564754492, + 20.000906742825123, + 19.999353409992693, + 19.999434881471227, + 19.998560322008196, + 20.000135904059597, + 20.000404525756167, + 19.99941419954162, + 19.998996561951554, + 19.999689477906166, + 19.99884647521916, + 19.999575623433877, + 19.998809129351322, + 19.99997300076215, + 19.99877970064516, + 19.9986422002851, + 19.999150479525547, + 19.999665848541127, + 19.99973730186441, + 19.99937761866253, + 19.99978482507997, + 19.998924101419394, + 19.998970621685768, + 19.998851910206966, + 19.999466675332584, + 19.999012459657827, + 19.99999670761472, + 20.00033550221448, + 19.99882829984505, + 19.99927889987967, + 20.000443565627247, + 20.0007435378016, + 19.998846644295554, + 19.99960354272448, + 19.99981470268171, + 19.999935712317864, + 20.000649477500996, + 19.999900140361703, + 19.99865427841497, + 19.999142178288174, + 19.99983776063719, + 20.0000018870871, + 19.999863088534703 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.99948984358273, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/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": 19.99948984358273, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 248.35155773162842, + "eval_ep_s": 4.96703115940094, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L5_latency/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_L5_latency/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4c51ac7656fb63c58161cfa4bdc8526881877f24 --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ca91e9364cc4a6ab596b9cc23680a6fbff0cc28eb53f55ac98d9cec3d4f926 +size 509342 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ff7fe192bad672870b34cdc49ef69750eca1efd6 --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebd984317975d2396d1b14cc9bd1570c1ec2f062db172c791be8299f73cdebf +size 424578 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..74a80011591eb1988a660636c17419f4604d0899 --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085176aebbcea0601b2eca62043008bedac6d6a5c8b31eaf0736c52b556f2982 +size 524098 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8aee92376d8610a7acedb453ad6362c07ffe281f --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d14f8e7699574ee69b9aa27ec6dad5d2e1eef83fa1e403feacb3eb44091ecac +size 484906 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0f85cfc1a2a8abe80592bbb0872e3bb1e49f7055 --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2536ea26429677bb03ae8f56f21dc016cb302079f4c07fef6be6b2ad4714e7 +size 457363 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..79d0f8a06be5eacae35cada41cc2f57de26e1109 --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d456f03b13c21dff4d786d41f269537b02eb41309ba6059aa3b237a68ca127c1 +size 490838 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e5044fd6de8a8ac60a1b2a09d55d5b2bee19cfce --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9af53ffed5912bce4f8cf3ee003ce1d25338bf59aa33f1b3e8d1d62739f202 +size 474233 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..faa55599fef4607b22f73879cceca0b725b4f6e3 --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174087a956451333d614897f576abee5adf7e310c51f92d5cb40575d51d66037 +size 437480 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f9d3e32308de9000badf42ee661e6f66c5f8226c --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f702d79bbff1bd228d26fa7a419db03d8ce900ee30c92065518ef1acb19e5ce +size 417040 diff --git a/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e5ec36cf122a4e8ab0ab91d381c3928eeb2d90da --- /dev/null +++ b/eval/planbind_L5_latency/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083dd0cc968df2ce6693568767efc3c5a7096e7bf913896d599eeedb2a4f99a0 +size 439145 diff --git a/eval/planbind_L6_latency/eval_info.json b/eval/planbind_L6_latency/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3d69faa480fdce73ef38fbcfed118bb67e1b19ae --- /dev/null +++ b/eval/planbind_L6_latency/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99920067423207, + 19.999374339760724, + 19.999263424665827, + 19.999186169088336, + 19.99926540445156, + 19.99931262361049, + 19.999103212934052, + 19.99941349783628, + 20.000912392296385, + 19.99935454374684, + 19.999407544222077, + 19.998560366414353, + 20.000242626410746, + 20.000404150117326, + 19.99929530569687, + 19.998990789378848, + 19.999694329405205, + 19.998856673655915, + 19.999556941521845, + 19.999456757752444, + 19.99996755138518, + 19.998779770478627, + 19.99864167319429, + 19.999150446505546, + 19.999665854449287, + 19.999744424497504, + 19.99937721821303, + 19.999757890689537, + 19.998924143025462, + 19.99897062168577, + 19.998853125529774, + 19.99946562200456, + 19.99902266588925, + 19.999995812824643, + 20.000331841004503, + 19.998825185238324, + 19.999278899879666, + 20.000482566964525, + 20.0007459164613, + 19.998847267297926, + 19.999605270987423, + 19.9998157600556, + 19.99997471411895, + 20.000664351578944, + 19.99926295814083, + 19.998661329876942, + 19.999792463094657, + 19.999818380585516, + 19.999999717416813, + 19.99982980798266 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.999502100365106, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/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": 19.999502100365106, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 222.37499451637268, + "eval_ep_s": 4.4474999046325685, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency/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/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2dabbba12d7c36b67af6366688c7aa496188e218 --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1599abbadebf5a5398e889bdc3f762ddad08f565862d4bbdf0a9748bab421289 +size 510567 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c92b9b0dd3c33a1840ffc6873baf36881503b248 --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea6b64fa4b811a9eb00cd928cc072e1ff52c09ee560fcd849b71679c94cf3a8 +size 423484 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ad1fac0d57ba3fa7c34963287b94818257b12ab4 --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4554d970b179ba536118d99562def52fa3b608bc07d49af23b0e4296f7b53551 +size 520924 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..48f252ca06c39fd6e6839275df607111972e0e92 --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745b7472b7d22c76a6bfbfb5e6a95093dd6ec9070b1e73f568c0ad78585e3c13 +size 488028 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..54bb3bc6ebfb878d7d84c41d87d42b877c1dd68b --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418942a4a921c34c68e94939c7cca8efc9b056a6f353c1087938e0132781db7c +size 459182 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9273f5b75f2b0e3d0c3f8748d026a2dffa42063c --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405fe16c4b3bb5bcd8f41103a7e0834390efbca50e16c25668dbaa814eb06ffe +size 486212 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..27320cf2f5a3721528652a8a5b244683c4c8301d --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd24507b8321420023d257dc406866b4437681d7d375fdb27d9c867080c05d2b +size 472500 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3aaa9038c45963366056315ca61148fe769ed373 --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd63362efc0d343e44a41e4e1719a3917edb1351dd70444087505ba298305a2 +size 437462 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3345ba3cd6f7d2af0e537ab0d33eb5270ad9ddd1 --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404069cb1038d2c65f97a59070fbc4dd81f4a665e7c3753de906c4d01dd32f8b +size 416000 diff --git a/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..33c82483b8e75af2d99c2ba528a41f20f43b2f6f --- /dev/null +++ b/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eddf95f600973f2454af6137155c07990d397373980a80c9b4fe6b7613c8b62 +size 442026 diff --git a/eval/planbind_L6_latency_shift3cm/eval_info.json b/eval/planbind_L6_latency_shift3cm/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ec33f38a35fca675be3c04d558e129643e7ea39d --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999751603106922, + 19.99943418267172, + 19.99926102920657, + 19.999186185589036, + 19.999008127868276, + 9.999063347077, + 19.999084089109253, + 19.999422321500656, + 20.000718611155836, + 19.999361909145925, + 19.999450960589694, + 5.272005355283752, + 19.99993808179158, + 20.00033522085595, + 9.99929530569687, + 19.999087333368372, + 19.999613063137765, + 19.99879078618209, + 19.999389307456717, + 9.99880912935132, + 19.999849473228938, + 9.998493250340507, + 19.998874751060157, + 9.99896791012983, + 19.99966585285246, + 19.99969119067518, + 19.999375192327758, + 9.998683241697425, + 19.998922403888905, + 20.00087035478629, + 19.9987625763449, + 19.999503194030837, + 19.999238868291684, + 20.000309294969934, + 20.000627326554177, + 19.99879578247197, + 19.999278899879666, + 20.00067483457487, + 20.000882478256898, + 19.99862465637558, + 19.999735537071327, + 19.99982156375354, + 20.000138727595342, + 20.0011585618781, + 20.00029501323754, + 19.998554978826355, + 9.999142178288173, + 19.999797103265955, + 19.999816072326006, + 19.999832978305985 + ], + "max_rewards": [ + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 9.749651036621955, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 9.523854646540542, + 10.0, + 10.0, + 4.794634156303487, + 10.0, + 10.0, + 10.0, + 10.0, + 4.590080485810422, + 10.0, + 8.480247487962238, + 10.0, + 4.599487694945692, + 10.0, + 10.0, + 10.0, + 8.583456245042363, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.6817023959512523, + 10.0, + 10.0, + 10.0 + ], + "successes": [ + true, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + false, + true, + true, + false, + true, + true, + true, + true, + false, + true, + false, + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + true, + true, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/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 + } + ], + "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": 50, + "n_success": 42, + "pc_success": 84.0, + "pc_success_ci95": [ + 71.485783936965, + 91.6625793219666 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 18.30498780394863, + "avg_max_reward": 9.44006228298356, + "pc_success": 84.0, + "n_episodes": 50, + "n_success": 42, + "pc_success_ci95": [ + 71.485783936965, + 91.6625793219666 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/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": 18.30498780394863, + "avg_max_reward": 9.44006228298356, + "pc_success": 84.0, + "n_episodes": 50, + "n_success": 42, + "pc_success_ci95": [ + 71.485783936965, + 91.6625793219666 + ], + "eval_s": 332.49587631225586, + "eval_ep_s": 6.64991753578186, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_shift3cm/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_shift3cm/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5fc6958a655bc5e91e80093aef1ca168b1142f1c --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8095e343622ed041848038979591f5f7031cf903fe42a15fc1d6fc6d9271c2 +size 478572 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3d4a5fb40e99a4a6a7fac10c0680233ef1674e31 --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ba72424137ae2c11121809562bc6d638863fd69b3d51a1b9fbf258d3459e8c +size 433625 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..83804b308018baa72598c0627d979dab8df38d1b --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32fe04ae6f9659f9840f8c066635a681d68040567c159e814ae6bde1e06fe8c7 +size 487455 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..65bcbdc4d13a65486e686342e4e2956f45899321 --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba7d92abdb9260fc9ab5acb6f911ff37655a285215fabf46df51e1a6bbdd5e46 +size 500879 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3e97b62224b73ef12c3a6cf28e1a4bf3dd26d380 --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888267aaaeeae47c0cafe81885cbda73aae3711096c3528d3799eef6d3c7b2a0 +size 490325 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1fdabf3473c9e5e583ca8c0e2318675cf84cbe72 --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba25b954364d859bbf779dabc75b2ac2acf24d910b9132d2f60a9a0a1616b6f +size 1030577 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..95bd61deb0074ded2fded582efc2f92ec19de77b --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd5acae02ce75cbe377ad16affc1c03cabefdb7bac67b96b4a07c8b210f6f683 +size 498018 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4a8ac26eaaf414700f26053c75aa1a1340f59fd3 --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea832ece6c575dc69543dcc29f3b4c43655de2066f1c239f58ce998df386bd86 +size 428775 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..afcb80e1a1d786dcb77ec6d93497d7649e439b45 --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea774a70561434ab8969f5c7d8587cfe93dc557bbdac28ff333b1d416efc0915 +size 414189 diff --git a/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..581b74949607bd525b21c6b9850085474522b9ce --- /dev/null +++ b/eval/planbind_L6_latency_shift3cm/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8650fc4a1fede5490403eb5ffd43e36e036944bb9a469437c9239cfe63df614 +size 464308 diff --git a/eval/planbind_L6_latency_tau0.5/eval_info.json b/eval/planbind_L6_latency_tau0.5/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..c09c685b9f9d68cf14d38c1b276d11d3e2bf4492 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999741735137267, + 8.999209033300794, + 19.9992610000145, + 19.99918784355147, + 19.999210529841235, + 5.062649605498564, + 19.999108567805074, + 19.99941166757574, + 20.001029821233544, + 19.999356523734686, + 0.02793776805091397, + 19.99857490531428, + 20.000227804597824, + 20.000411503569033, + 19.99940792125846, + 19.99897261193412, + 19.9996719098199, + 19.99885753821458, + 19.99954185588102, + 19.999456924726182, + 0.1695784629887095, + 0.08419349328725045, + 19.998633969128772, + 0.09984398689871976, + 19.999665839034755, + 0.15229843461174553, + 19.999384239715294, + 19.999806604795147, + 19.998964140971314, + 20.000618791430554, + 19.99886206680973, + 19.999459664403638, + 19.99901939683839, + 19.999975571568942, + 5.077350597555162, + 9.998585489611028, + 19.99985605129211, + 0.2093531658723341, + 20.000684023938703, + 0.07054057373679856, + 0.20244544197146375, + 19.999821814636995, + 19.99998214249117, + 20.0007236775028, + 19.999795813555078, + 19.998658239717273, + 0.01212998123582032, + 5.100194648082734, + 0.17867097662937426, + 19.999824267332713 + ], + "max_rewards": [ + 10.0, + 1.5881212536900127, + 10.0, + 10.0, + 10.0, + 1.5614641622547436, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3625345629482875, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.3705767916143559, + 1.1660352348556011, + 10.0, + 0.0291688984820766, + 10.0, + 1.1999036337041424, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.579892277323447, + 1.5800627880677673, + 10.0, + 1.3339575990907022, + 10.0, + 0.02691120968483962, + 1.3241730622452623, + 10.0, + 10.0, + 10.0, + 10.0, + 10.0, + 1.2449374456433504, + 4.782452663471396, + 1.305679510309862, + 10.0 + ], + "successes": [ + true, + false, + true, + true, + true, + false, + true, + true, + true, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + false, + true, + false, + true, + true, + true, + true, + true, + true, + true, + true, + false, + false, + true, + false, + true, + false, + false, + true, + true, + true, + true, + true, + false, + false, + false, + true + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/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": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": 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": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": false, + "nested_middle": false, + "released_middle": false, + "picked_top": false, + "nested_top": false, + "released_top": false + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": true, + "released_top": true + }, + { + "picked_middle": true, + "nested_middle": true, + "released_middle": true, + "picked_top": true, + "nested_top": 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": 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": 80.0, + "pc_nested_middle": 80.0, + "pc_released_middle": 80.0, + "pc_picked_top": 80.0, + "pc_nested_top": 74.0, + "pc_released_top": 72.0 + }, + "n_episodes": 50, + "n_success": 35, + "pc_success": 70.0, + "pc_success_ci95": [ + 56.249649535546595, + 80.89644649911905 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 14.708602972774074, + "avg_max_reward": 7.4291174218677165, + "pc_success": 70.0, + "n_episodes": 50, + "n_success": 35, + "pc_success_ci95": [ + 56.249649535546595, + 80.89644649911905 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 80.0, + "pc_nested_middle": 80.0, + "pc_released_middle": 80.0, + "pc_picked_top": 80.0, + "pc_nested_top": 74.0, + "pc_released_top": 72.0 + } + }, + "overall": { + "avg_sum_reward": 14.708602972774074, + "avg_max_reward": 7.4291174218677165, + "pc_success": 70.0, + "n_episodes": 50, + "n_success": 35, + "pc_success_ci95": [ + 56.249649535546595, + 80.89644649911905 + ], + "eval_s": 378.86705684661865, + "eval_ep_s": 7.577341151237488, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_9.mp4" + ], + "predicted_video_paths": [], + "pc_picked_middle": 80.0, + "pc_nested_middle": 80.0, + "pc_released_middle": 80.0, + "pc_picked_top": 80.0, + "pc_nested_top": 74.0, + "pc_released_top": 72.0 + } +} \ No newline at end of file diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..328b016f6dac9f3b9267bbed2c45a1a2e60c2eff --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6037f38e2b481be70ecfb6b041eee5b13752fb629993b046ea0c7201d93db5a +size 513974 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6f713570d25a443f62a981302e9934476b3d3cf7 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839233172f9e301211f0ce240c3a0a50c36c8c8c1268a40429f8ba81e7ebda20 +size 892247 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..954b039c3bc5598e5aeda79ccccd48427e48bc12 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de374a9527fc7f6a89dae87ce53e1d4bb170118258fb2e3499aa883ae4e3422d +size 517548 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..672b4cc0b4e960ee808a638811898fa0752ca86d --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24bc2ab0d0453268f0f3828531ed2ec0f276811f44be4239566b42e5d372f00 +size 475961 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..98796fefe06f86ce15c62d56472fa16a2ef9619f --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0390f2ec5c7f3c08e7f85d8c650c46ab56eef2792c24637c2ea3433274dbd9 +size 480546 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c5ac9b335da0f25c3337b0b7c000d130b10b87f9 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7c19a3f76f890ad9371840838485acb87f7047cd4beb4b06d062d987043ea8 +size 1098482 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c8530fc6d3d29de8e4ab45157212c7c5f1ff77a0 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c966eab865b4dd8dbd43d960bd0266c58ad4910f475f891900e1c42d5f83d8d8 +size 466843 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8b538c65a9484abfdcc6db0e21444660eebe8b04 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30e353b18b0428b8feb6fcaa277d3e13e27348699ea8cba1f1b577c04c9134a +size 417081 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a35852e129f039652fc5713f2621009f94ae474d --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43a6ad7b3aff3fe744c44f3f76cb80fa89e2cba35469bd39daaca1e72480827 +size 413605 diff --git a/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..986dc1324e5accc565ed55ee7241d2b31888e278 --- /dev/null +++ b/eval/planbind_L6_latency_tau0.5/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752da25a53059bcc90606251135d975d897aaba3fb361826c9e6340820e50494 +size 445082 diff --git a/eval/planbind_L6_latency_tau1.0/eval_info.json b/eval/planbind_L6_latency_tau1.0/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..fe123896c8f9403b1a93ca2d921b7b9611728c95 --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974173766371, + 19.999358590265192, + 19.99926323494003, + 19.99907126821248, + 19.99923430076136, + 19.999321506129974, + 19.99910597843756, + 19.99940394201387, + 20.00094950091798, + 19.999348980513766, + 19.999290942134582, + 19.9985667819137, + 20.00024087964805, + 20.000489103692892, + 19.999411081490425, + 19.998991828436242, + 19.999697824425503, + 19.998858349052963, + 19.9995531617391, + 19.999456907674258, + 19.999919582061093, + 19.998493250340513, + 19.99865619107643, + 19.999150496890216, + 19.999665853984002, + 19.999771472964063, + 19.999383988028335, + 19.99983044342824, + 19.99892396455946, + 20.000633495692128, + 19.99887487587331, + 19.99879684881501, + 19.998993782295166, + 19.999967415370968, + 20.000385234182676, + 19.998818226193738, + 19.999831044112653, + 20.00039640000951, + 20.000673652660886, + 19.998842868405422, + 19.999646507016077, + 19.999813946225935, + 19.999891552174404, + 20.000724865434925, + 19.99976350929166, + 19.998600547017094, + 19.99979765809929, + 19.999818792545476, + 20.000021754514012, + 19.99902290285638 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.999529340443654, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/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": 19.999529340443654, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 216.14851188659668, + "eval_ep_s": 4.322970247268676, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_latency_tau1.0/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_tau1.0/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..079b9abcaa382cf537eab1009227dee23dd5f84f --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa3a6f0d1419583ef1434321e864c5b3a4dfc367259b854bfce431f39affc02 +size 488815 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8f570047f66ed194d472358daf954a516e8a1b3d --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e42bc7523562ce2c62db8e9fc2220b678195567282f34ac8f64fd7dedba1493 +size 435340 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1f02ddab9ee63e6467a11b1fae543173e2007cdd --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7a80e0eca2d57ee26f0f40409098345bb4a9c97cb4ac2985c1472f05c48df0 +size 489928 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..16095eb364fd69bf5b85c4a602ea85c1b5bb7f8c --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:746e324e29645fbbe0ca1d0705285d5d853535e005ecdf4efd33fc3f567ed121 +size 487654 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..60ed9b5fbc1470e15c1733bd4386b89f8daf4891 --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39cd49cf13b21621a2466025374d8cedd98c0571dfda1d071527c7c0e458be60 +size 490225 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..329922db3cd3ba5ac970cc220f524f9aa03a351b --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5603da4f3783fe6ebea18390ed25827d3ad8f922c47bfd5345263cbf652c3e +size 474858 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6a2dd9d24ff140dd1c798199c38514f90240af85 --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1ceb58160676784b180e8b6452616d2c08458103101bff9bb25893f2eaaae9 +size 472249 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6f41d8c5e405a11014c2481436435be74bbaae37 --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45af28a607e0dd26fb7c362de01689b12c77f59f9c63342fcf0dd883642f8ffc +size 429403 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8913e20ecae2e207e07e409f2498e970a5aa9bc2 --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d1e34e8c2c432c2b58411002b18e497696e331ed1286086334c45b82e0908d +size 415768 diff --git a/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f6e0280d1154daffe78fce77706e6207bff5c06a --- /dev/null +++ b/eval/planbind_L6_latency_tau1.0/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31418e5f558ed1b24a45cbcd7d50b65e93223f925d37d16dab60acbcd9e5a7c1 +size 446204 diff --git a/eval/planbind_L6_none/eval_info.json b/eval/planbind_L6_none/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1dcd86e1e6b0177316290e77ee673ea5fbc2fad4 --- /dev/null +++ b/eval/planbind_L6_none/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.99974165444038, + 19.999371593600777, + 19.998804710018963, + 19.999190857673927, + 19.999281224695338, + 19.999350664481053, + 19.999097562438692, + 19.999379610686784, + 20.000872170407842, + 19.999352183323197, + 19.999450739515037, + 19.9985596154334, + 20.000237532974122, + 20.00040514312591, + 19.999427616846397, + 19.999048312661127, + 19.999670475902796, + 19.998839706102192, + 19.99949434469164, + 19.998809129351322, + 19.999998737442272, + 19.998779619287642, + 19.998634114070548, + 19.99915077160236, + 19.999665841494647, + 19.999738121675257, + 19.999375410595704, + 19.9997363991724, + 19.998804131560927, + 20.000676850022618, + 19.998864021073345, + 19.999470617551832, + 19.99899344327407, + 19.999938429427367, + 20.000304786917464, + 19.998817478830688, + 19.99927889987967, + 20.00032582935603, + 20.000711240732464, + 19.998853914577882, + 19.999558722240998, + 19.999794043899495, + 19.999901564656668, + 20.000572263238006, + 19.999861003151278, + 19.998641465604543, + 19.99979391018288, + 19.99982217151333, + 19.99842793257527, + 19.99990009170658 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.999495533513702, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/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": 19.999495533513702, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 220.8586618900299, + "eval_ep_s": 4.417173247337342, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_none/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_none/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b2b369cd6cb7d6a69849c0291cca915cfb4efab8 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a0800ea8397aecca53edfe9583e69f13ec3dd13cbbda564d96198f2df73cf3 +size 509374 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c75a886cde875e2fb50539b401eac97542bdc743 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced2fa3fe74a2436cef5fda2eb895bb08df1e54b38a021e3061e08a395d046e6 +size 424700 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..29216d425e5b7f2aa7868fd0ced18bcf40aad862 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ae0ddf0ce061e17f3c428dd06dbb009902566fa4b42de3e71c2d9d9bb38241 +size 532583 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d27b72768ca30587b82cbef5878ea0119e7e96c6 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523aa6fd85c3db8a2e0fecd98224c15d1acbcd2f8f29f059864929902b9ce221 +size 483079 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fe19051f4b024b077abe26899f0468ce28dc97b8 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6013a090e11f6571148b1b50d981adcf0921e199df8a1c63f2a5fa4d746b5b6c +size 453521 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fa377d9582132a6f58ab674dc0d794ea26f54f77 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c9e854cddda8c710557fec5f23d7bb7f5cafb46c1d65e9886b9caa8d2207a6 +size 507541 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c1587da1bf4e2e2a26e7fa4023495fa42036adaf --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96be1e0fe493ed02cc03abab32d1dde436412d4ec7c1657ffc42cc76b1cbd2d +size 472458 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d8231e7a294e14dcffc110e51b512d6f71b2a74c --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd471ef65b3b20218fa2fdfda33c59458e56df26e93693220ff72b5284dd95ee +size 432500 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fbc83d247d2572851982c0f5182cfbad16f38a86 --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1ebbf60d25761ec42c798b1885fbf3e226a682e0bbcef6b38ed9034403c0a5 +size 414210 diff --git a/eval/planbind_L6_none/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9f2492a81487f49249402bb4d42cef018b3a02ab --- /dev/null +++ b/eval/planbind_L6_none/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acdcc0ab167c9e2e98776f035b0e5ea8fe1348bb7c63f5f292bef2d4167e296a +size 442667 diff --git a/eval/planbind_L6_now/eval_info.json b/eval/planbind_L6_now/eval_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b61e063f1f9fb54aefd6a729d0743ae9086fed18 --- /dev/null +++ b/eval/planbind_L6_now/eval_info.json @@ -0,0 +1,658 @@ +{ + "per_task": [ + { + "task_group": "nexarm", + "task_id": 0, + "metrics": { + "sum_rewards": [ + 19.999743759151706, + 19.999359675658397, + 19.999266893155838, + 19.999071268212475, + 19.999271081138346, + 19.999333400454137, + 19.999097476384062, + 19.99939517635427, + 20.00088129790871, + 19.999352933441266, + 19.999468711719814, + 19.99856047722613, + 20.000122290507704, + 20.00044611039428, + 19.99929530569687, + 19.999039954338, + 19.99964868549794, + 19.99884426028236, + 19.999530395683472, + 19.999456848002726, + 19.999954415083486, + 19.998493250340516, + 19.998622696659698, + 19.99915073091822, + 19.99966584073759, + 19.999765744114626, + 19.99937712658319, + 19.99973095118758, + 19.99892410052816, + 20.00062316465895, + 19.998864231672464, + 19.999465985842356, + 19.999013229732956, + 19.999991171553344, + 20.000225225301197, + 19.99882545758639, + 19.99927889987967, + 20.000388746624697, + 20.00071623383015, + 19.998855391796436, + 19.999570769171623, + 19.999802729350886, + 19.99989042018758, + 20.000695087775163, + 19.999262958140825, + 19.998673351201575, + 19.999792774496495, + 19.999834725775997, + 20.00003205330099, + 19.999818210931355 + ], + "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 + ], + "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 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/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 + } + ], + "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": 50, + "n_success": 50, + "pc_success": 100.0, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ] + } + ], + "per_group": { + "nexarm": { + "avg_sum_reward": 19.999529833523454, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/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": 19.999529833523454, + "avg_max_reward": 10.0, + "pc_success": 100.0, + "n_episodes": 50, + "n_success": 50, + "pc_success_ci95": [ + 92.86524008666413, + 100.0 + ], + "eval_s": 228.13389921188354, + "eval_ep_s": 4.562677989006042, + "video_paths": [ + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_0.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4", + "/home/marinelab/code/plan-bind-d2/experiments/261028-plan-bind-d2-latency/outputs/full/eval/planbind_L6_now/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_now/videos/nexarm_0/eval_episode_0.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fcebea5f7479e6d5abeaed1dabbfdffeff6ff26f --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5706c04084bf241929db2536459e3d23db9782b5b8c90c31768acc9bc5f537f +size 500621 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f8557cb5dcb9cac8b1c82044d6e1b9c9c69da55f --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb225363981f9a41ee6fe4a374d8988ff833792311396107dc5b20bb5731e20e +size 429694 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..41ade68b191a2a50aa3154f980379288233415d2 --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38acecef2620bc2e673c45cab75b4d7f7f28983d473753dcfe8d33fca833d1fa +size 516101 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..284014610cc34b23dd5f0879a1da421556bb0589 --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3657a2e51c62154be2b732f4ea467cb4d133ac1be9ffca57ce3f5bab80b8fb38 +size 742283 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..521ce55328d7521e7e6a8508ea7620da94db1432 --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd338843d74252e032eaacd39081eb6fdc7a420a0a9eb522670cf5dc75eb149 +size 452609 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..36ae4380e1e92a4eab26cfbb410a9bae1296eeeb --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_5.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656dcdda888120d2fbf7f88c6a1283b1de5b7d1b8c29978d6197b47eb42edea6 +size 507614 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..176851da8387ae7626688eaf256168498005d267 --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_6.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69be77905129c807423105b3fb394e590db3c067f9d6174c185851ae56da508e +size 471947 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0751a1319da07c35b962f1b3edbc4b332c4ac9a5 --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_7.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f3857db7bd1c2eac9280b5f792c7f14536a596031f10529f6d0e261d72fad74 +size 433646 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..21a06ed5d55dac4ebd676730d1cfeb1de109a4ef --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04704156073952ce88bafb4fa82291096d6fc96985d7c7092012f7ece0d19c0e +size 412889 diff --git a/eval/planbind_L6_now/videos/nexarm_0/eval_episode_9.mp4 b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_9.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e8e742f6770bfcdf9faa6adb4a49be59142b3c71 --- /dev/null +++ b/eval/planbind_L6_now/videos/nexarm_0/eval_episode_9.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ccbb25f9532f7e9e5e4e29c24204695824567182c06f80a7871c453eb85746d +size 440794