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": [
19.999741729105217,
19.99936732025145,
19.99926099854716,
19.99907126821248,
19.999266848449444,
19.999354672166376,
19.99910395065403,
19.999438804109364,
20.000835921777018,
19.999348244197392,
19.999460881203017,
19.998560053416025,
20.000131253628357,
20.000371156592486,
19.99941820945686,
19.999012573224917,
19.99969482121358,
19.99887855688067,
19.999507578620545,
19.998809129351322,
19.999858320571295,
19.998779620436913,
19.998648923962104,
19.999150669781667,
19.99966576923953,
19.99976107153895,
19.999377924530517,
19.999764599863475,
19.99880413156093,
20.000637351865425,
19.998878925172754,
19.99946021740557,
19.999001482548525,
0.39090039838235235,
20.000381421795346,
19.99882611209254,
19.99990145464373,
20.000288473417545,
20.000695189920393,
19.998861150931422,
19.99965705850569,
19.999821137388622,
19.999867678320353,
20.000650498830808,
19.999787285028482,
19.998624826794313,
19.99914217828817,
19.999821652787944,
19.999885596712595,
19.999887837946147
],
"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,
1.3627806665762374,
10.0,
10.0,
10.0,
10.0,
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,
false,
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_L0_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/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": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": 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": 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": 19.607348458626436,
"avg_max_reward": 9.827255613331523,
"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_L0_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/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": 19.607348458626436,
"avg_max_reward": 9.827255613331523,
"pc_success": 98.0,
"n_episodes": 50,
"n_success": 49,
"pc_success_ci95": [
89.50455641036218,
99.64607407283539
],
"eval_s": 470.1347904205322,
"eval_ep_s": 9.40269582271576,
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L0_latency/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
}
}