thanhkt's picture
Upload eval from run_all.sh
188d9aa verified
Raw History Blame Contribute Delete
20.9 kB
{
"per_task": [
{
"task_group": "nexarm",
"task_id": 0,
"metrics": {
"sum_rewards": [
19.99974172245221,
19.999377606982573,
0.1213908880888468,
19.999186180689485,
19.99927127156011,
19.99929025335867,
19.99909761783959,
0.20095899838781917,
20.000911793112504,
19.999346235106835,
19.999432705113,
19.99855955755781,
20.000151407574265,
20.000416948316904,
19.999418892144345,
19.999031153130442,
19.99967798299173,
19.99885672148783,
19.999547286100146,
19.998809129351322,
19.999915400105895,
19.998779702861004,
19.998629094607345,
0.2754417521815774,
19.99966584275329,
19.99974386117366,
19.999378221964378,
19.99977748723414,
19.998924151098585,
20.00068167475917,
19.99883905072482,
0.04393698809563096,
19.999017145286114,
20.000002096743927,
20.000231426807275,
0.2839215112123241,
19.999831177008694,
20.00044198500332,
20.00064826336177,
19.998869625630466,
19.99965456019887,
19.99980879868393,
19.999858906268287,
0.21395532105883497,
19.999889454688994,
0.5424283203450395,
19.99979807347814,
19.999853140087026,
19.999977174901133,
19.999933768817062
],
"max_rewards": [
10.0,
10.0,
1.1248502086697418,
10.0,
10.0,
10.0,
10.0,
1.338261960222675,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
1.1350217350429417,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
0.029531961670468343,
10.0,
10.0,
10.0,
1.1721251314390504,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
1.256488369397799,
10.0,
5.019918127786827,
10.0,
10.0,
10.0,
10.0
],
"successes": [
true,
true,
false,
true,
true,
true,
true,
false,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
false,
true,
true,
true,
true,
true,
true,
true,
false,
true,
true,
true,
false,
true,
true,
true,
true,
true,
true,
true,
false,
true,
false,
true,
true,
true,
true
],
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_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": false,
"released_middle": false,
"picked_top": false,
"nested_top": false,
"released_top": false
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": 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": false,
"nested_middle": false,
"released_middle": false,
"picked_top": false,
"nested_top": false,
"released_top": false
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": false,
"nested_middle": false,
"released_middle": false,
"picked_top": false,
"nested_top": false,
"released_top": false
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": false,
"nested_top": false,
"released_top": false
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"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": 88.0,
"pc_released_middle": 88.0,
"pc_picked_top": 86.0,
"pc_nested_top": 86.0,
"pc_released_top": 86.0
},
"n_episodes": 50,
"n_success": 43,
"pc_success": 86.0,
"pc_success_ci95": [
73.81380628941446,
93.04916657298371
]
}
],
"per_group": {
"nexarm": {
"avg_sum_reward": 17.233286166569744,
"avg_max_reward": 8.82152394988459,
"pc_success": 86.0,
"n_episodes": 50,
"n_success": 43,
"pc_success_ci95": [
73.81380628941446,
93.04916657298371
],
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_9.mp4"
],
"predicted_video_paths": [],
"pc_picked_middle": 94.0,
"pc_nested_middle": 88.0,
"pc_released_middle": 88.0,
"pc_picked_top": 86.0,
"pc_nested_top": 86.0,
"pc_released_top": 86.0
}
},
"overall": {
"avg_sum_reward": 17.233286166569744,
"avg_max_reward": 8.82152394988459,
"pc_success": 86.0,
"n_episodes": 50,
"n_success": 43,
"pc_success_ci95": [
73.81380628941446,
93.04916657298371
],
"eval_s": 587.4381749629974,
"eval_ep_s": 11.748763513565063,
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L3_latency/videos/nexarm_0/eval_episode_9.mp4"
],
"predicted_video_paths": [],
"pc_picked_middle": 94.0,
"pc_nested_middle": 88.0,
"pc_released_middle": 88.0,
"pc_picked_top": 86.0,
"pc_nested_top": 86.0,
"pc_released_top": 86.0
}
}