ppo-Huggy / run_logs /timers.json
CharithAnupama's picture
Huggy
191218d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042059183120728,
"min": 1.404204249382019,
"max": 1.426580548286438,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70493.9453125,
"min": 69388.5078125,
"max": 75828.6328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 68.88145048814505,
"min": 68.202216066482,
"max": 411.4836065573771,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49388.0,
"min": 49095.0,
"max": 50201.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49939.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49939.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.530606508255005,
"min": 0.027775174006819725,
"max": 2.530606508255005,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1814.44482421875,
"min": 3.3607959747314453,
"max": 1814.44482421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.058783555379971,
"min": 1.7560143076683865,
"max": 4.090304133933295,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2910.1478092074394,
"min": 212.47773122787476,
"max": 2910.1478092074394,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.058783555379971,
"min": 1.7560143076683865,
"max": 4.090304133933295,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2910.1478092074394,
"min": 212.47773122787476,
"max": 2910.1478092074394,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677319482033555,
"min": 0.013688603256984302,
"max": 0.018714173174036355,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05031958446100665,
"min": 0.028456494283940023,
"max": 0.05537326088233385,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0645919546071026,
"min": 0.021076209843158722,
"max": 0.0645919546071026,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1937758638213078,
"min": 0.043627166437606016,
"max": 0.1937758638213078,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.913548695516675e-06,
"min": 3.913548695516675e-06,
"max": 0.0002953641765452749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1740646086550025e-05,
"min": 1.1740646086550025e-05,
"max": 0.0008443291685569499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130448333333335,
"min": 0.10130448333333335,
"max": 0.198454725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30391345000000003,
"min": 0.2077432,
"max": 0.5814430500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.509371833333346e-05,
"min": 7.509371833333346e-05,
"max": 0.004922890777499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022528115500000036,
"min": 0.00022528115500000036,
"max": 0.014074008194999998,
"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": "1763441933",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
"command_line_arguments": "/content/py310/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1763444543"
},
"total": 2610.410661377,
"count": 1,
"self": 0.4327794780001568,
"children": {
"run_training.setup": {
"total": 0.03009193699995194,
"count": 1,
"self": 0.03009193699995194
},
"TrainerController.start_learning": {
"total": 2609.947789962,
"count": 1,
"self": 4.539595982917035,
"children": {
"TrainerController._reset_env": {
"total": 3.1800420949998625,
"count": 1,
"self": 3.1800420949998625
},
"TrainerController.advance": {
"total": 2602.129115309083,
"count": 233195,
"self": 4.920027005956854,
"children": {
"env_step": {
"total": 2116.2047046510834,
"count": 233195,
"self": 1704.7743939861045,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.47832995890167,
"count": 233195,
"self": 15.543648951912928,
"children": {
"TorchPolicy.evaluate": {
"total": 392.93468100698874,
"count": 222917,
"self": 392.93468100698874
}
}
},
"workers": {
"total": 2.9519807060771655,
"count": 233195,
"self": 0.0,
"children": {
"worker_root": {
"total": 2597.3845469749217,
"count": 233195,
"is_parallel": true,
"self": 1214.0886991748603,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008810869999251736,
"count": 1,
"is_parallel": true,
"self": 0.00023348700005954015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006475999998656334,
"count": 2,
"is_parallel": true,
"self": 0.0006475999998656334
}
}
},
"UnityEnvironment.step": {
"total": 0.04023189100007585,
"count": 1,
"is_parallel": true,
"self": 0.0003779149999445508,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027039799988415325,
"count": 1,
"is_parallel": true,
"self": 0.00027039799988415325
},
"communicator.exchange": {
"total": 0.03880022800012739,
"count": 1,
"is_parallel": true,
"self": 0.03880022800012739
},
"steps_from_proto": {
"total": 0.0007833500001197535,
"count": 1,
"is_parallel": true,
"self": 0.0002121039999565255,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000571246000163228,
"count": 2,
"is_parallel": true,
"self": 0.000571246000163228
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1383.2958478000614,
"count": 233194,
"is_parallel": true,
"self": 39.27284096902645,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.70282342205746,
"count": 233194,
"is_parallel": true,
"self": 83.70282342205746
},
"communicator.exchange": {
"total": 1168.1681049520134,
"count": 233194,
"is_parallel": true,
"self": 1168.1681049520134
},
"steps_from_proto": {
"total": 92.15207845696409,
"count": 233194,
"is_parallel": true,
"self": 32.5674474909747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.58463096598939,
"count": 466388,
"is_parallel": true,
"self": 59.58463096598939
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.00438365204286,
"count": 233195,
"self": 6.628048978923061,
"children": {
"process_trajectory": {
"total": 161.2817682671216,
"count": 233195,
"self": 160.19786327412226,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0839049929993507,
"count": 10,
"self": 1.0839049929993507
}
}
},
"_update_policy": {
"total": 313.0945664059982,
"count": 97,
"self": 248.85308530300404,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.24148110299416,
"count": 2910,
"self": 64.24148110299416
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.850001904647797e-07,
"count": 1,
"self": 8.850001904647797e-07
},
"TrainerController._save_models": {
"total": 0.09903569000016432,
"count": 1,
"self": 0.0012402639999891107,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09779542600017521,
"count": 1,
"self": 0.09779542600017521
}
}
}
}
}
}
}