Huggy / run_logs /timers.json
kashishgupta's picture
Upload Huggy PPO model
c84df58 verified
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406705379486084,
"min": 1.406705379486084,
"max": 1.4287163019180298,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70985.1640625,
"min": 69394.015625,
"max": 75400.75,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.19741697416974,
"min": 83.37925170068027,
"max": 390.78125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49429.0,
"min": 48864.0,
"max": 50118.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999984.0,
"min": 49590.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999984.0,
"min": 49590.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.432265520095825,
"min": 0.1611679643392563,
"max": 2.472489356994629,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1318.2879638671875,
"min": 20.468332290649414,
"max": 1386.8900146484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7893931352124444,
"min": 1.906255129284746,
"max": 3.980270197588144,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2053.851079285145,
"min": 242.09440141916275,
"max": 2203.598031103611,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7893931352124444,
"min": 1.906255129284746,
"max": 3.980270197588144,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2053.851079285145,
"min": 242.09440141916275,
"max": 2203.598031103611,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013767500454398235,
"min": 0.013631874283055368,
"max": 0.019529237246994548,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0413025013631947,
"min": 0.027263748566110736,
"max": 0.057779238264386856,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055175283509824015,
"min": 0.02096804172421495,
"max": 0.058960153824753225,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16552585052947205,
"min": 0.0419360834484299,
"max": 0.17688046147425968,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3687988771000014e-06,
"min": 3.3687988771000014e-06,
"max": 0.00029534085155305,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0106396631300004e-05,
"min": 1.0106396631300004e-05,
"max": 0.0008439028686990499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112290000000002,
"min": 0.10112290000000002,
"max": 0.19844695000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30336870000000005,
"min": 0.20741770000000004,
"max": 0.58130095,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.603271000000004e-05,
"min": 6.603271000000004e-05,
"max": 0.004922502805000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019809813000000014,
"min": 0.00019809813000000014,
"max": 0.014066917404999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1775370163",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1775372738"
},
"total": 2574.6910021559997,
"count": 1,
"self": 0.4861749039996539,
"children": {
"run_training.setup": {
"total": 0.024756543999956193,
"count": 1,
"self": 0.024756543999956193
},
"TrainerController.start_learning": {
"total": 2574.180070708,
"count": 1,
"self": 4.3931101468069755,
"children": {
"TrainerController._reset_env": {
"total": 2.760396574999959,
"count": 1,
"self": 2.760396574999959
},
"TrainerController.advance": {
"total": 2566.9212881321932,
"count": 232271,
"self": 4.357533763331503,
"children": {
"env_step": {
"total": 2109.9442849748652,
"count": 232271,
"self": 1699.947631457764,
"children": {
"SubprocessEnvManager._take_step": {
"total": 407.31183049104266,
"count": 232271,
"self": 15.255059711118065,
"children": {
"TorchPolicy.evaluate": {
"total": 392.0567707799246,
"count": 223014,
"self": 392.0567707799246
}
}
},
"workers": {
"total": 2.684823026058666,
"count": 232271,
"self": 0.0,
"children": {
"worker_root": {
"total": 2561.0294864909383,
"count": 232271,
"is_parallel": true,
"self": 1186.817661068821,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007972859998517379,
"count": 1,
"is_parallel": true,
"self": 0.00025024899991876737,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005470369999329705,
"count": 2,
"is_parallel": true,
"self": 0.0005470369999329705
}
}
},
"UnityEnvironment.step": {
"total": 0.028782615999944028,
"count": 1,
"is_parallel": true,
"self": 0.000348933999930523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000213108000025386,
"count": 1,
"is_parallel": true,
"self": 0.000213108000025386
},
"communicator.exchange": {
"total": 0.027558063000014954,
"count": 1,
"is_parallel": true,
"self": 0.027558063000014954
},
"steps_from_proto": {
"total": 0.0006625109999731649,
"count": 1,
"is_parallel": true,
"self": 0.0001875059997473727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004750050002257922,
"count": 2,
"is_parallel": true,
"self": 0.0004750050002257922
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1374.2118254221173,
"count": 232270,
"is_parallel": true,
"self": 37.90619562824486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.11063108792291,
"count": 232270,
"is_parallel": true,
"self": 82.11063108792291
},
"communicator.exchange": {
"total": 1164.639057897898,
"count": 232270,
"is_parallel": true,
"self": 1164.639057897898
},
"steps_from_proto": {
"total": 89.55594080805145,
"count": 232270,
"is_parallel": true,
"self": 32.026636690129635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.52930411792181,
"count": 464540,
"is_parallel": true,
"self": 57.52930411792181
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 452.6194693939967,
"count": 232271,
"self": 6.6643585388912925,
"children": {
"process_trajectory": {
"total": 154.25235255710413,
"count": 232271,
"self": 153.1242449071044,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1281076499997198,
"count": 10,
"self": 1.1281076499997198
}
}
},
"_update_policy": {
"total": 291.7027582980013,
"count": 97,
"self": 229.4803994019942,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.22235889600711,
"count": 2910,
"self": 62.22235889600711
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.850001904647797e-07,
"count": 1,
"self": 8.850001904647797e-07
},
"TrainerController._save_models": {
"total": 0.1052749689997654,
"count": 1,
"self": 0.002061743999547616,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10321322500021779,
"count": 1,
"self": 0.10321322500021779
}
}
}
}
}
}
}