thanhkt's picture
Upload eval from run_all.sh (part 2)
99bd6ac verified
Raw History Blame Contribute Delete
21.1 kB
{
"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
}
}