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