thanhkt's picture
Upload eval from run_all.sh
188d9aa verified
Raw History Blame Contribute Delete
20.8 kB
{
"per_task": [
{
"task_group": "nexarm",
"task_id": 0,
"metrics": {
"sum_rewards": [
19.999200674232068,
19.999373972654343,
19.999261048852837,
19.999186161867463,
19.999284384404167,
19.999297282502006,
19.99910277111285,
19.999417094408823,
20.000888732496556,
19.999347707724787,
19.99941073659671,
19.998564270268854,
20.00017758734483,
20.00044425378418,
19.99929530569687,
19.99901637843433,
19.99969716296358,
19.998837030556043,
19.99952953394326,
19.999455908961806,
19.998443552681337,
19.99877967985564,
19.998634528302404,
19.99915253356425,
19.9996658745289,
19.999765118502168,
19.999377198678093,
19.999817386911296,
19.99892415940422,
20.000706000985968,
19.998824920716764,
5.015727369812351,
19.999001852734086,
19.999995867352215,
20.000367792811904,
19.99880598423951,
19.999848113509476,
20.000397522805137,
20.000698502358897,
19.998848203437092,
19.999624534506534,
19.999822804050225,
19.9999294386675,
20.000720365812555,
19.999262958140825,
19.99860247428985,
19.999797344992686,
19.999822631464124,
19.99998440791186,
19.99982155397148
],
"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,
4.780387397645839,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
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,
false,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true
],
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_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": false,
"nested_top": false,
"released_top": false
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"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": 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": 19.699839173516114,
"avg_max_reward": 9.895607747952916,
"pc_success": 98.0,
"n_episodes": 50,
"n_success": 49,
"pc_success_ci95": [
89.50455641036218,
99.64607407283539
],
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_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": 98.0,
"pc_nested_top": 98.0,
"pc_released_top": 98.0
}
},
"overall": {
"avg_sum_reward": 19.699839173516114,
"avg_max_reward": 9.895607747952916,
"pc_success": 98.0,
"n_episodes": 50,
"n_success": 49,
"pc_success_ci95": [
89.50455641036218,
99.64607407283539
],
"eval_s": 476.39677238464355,
"eval_ep_s": 9.527935461997986,
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L9_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": 98.0,
"pc_nested_top": 98.0,
"pc_released_top": 98.0
}
}