ppo-Huggy / run_logs /timers.json
VkumarStack's picture
Huggy
d5c8296 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053311347961426,
"min": 1.4053311347961426,
"max": 1.42628812789917,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71108.3515625,
"min": 69378.203125,
"max": 77551.28125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.97882736156352,
"min": 78.83572567783094,
"max": 359.72857142857146,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49107.0,
"min": 48869.0,
"max": 50362.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999906.0,
"min": 49813.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999906.0,
"min": 49813.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4052557945251465,
"min": 0.010296306572854519,
"max": 2.501448631286621,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1476.8270263671875,
"min": 1.4311866760253906,
"max": 1554.0989990234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6491391615098774,
"min": 1.8037939519762136,
"max": 4.0774219349872345,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2240.5714451670647,
"min": 250.72735932469368,
"max": 2436.1194791793823,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6491391615098774,
"min": 1.8037939519762136,
"max": 4.0774219349872345,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2240.5714451670647,
"min": 250.72735932469368,
"max": 2436.1194791793823,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.021686631288482913,
"min": 0.011847472863155416,
"max": 0.021686631288482913,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06505989386544873,
"min": 0.023694945726310833,
"max": 0.06505989386544873,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06168217621743679,
"min": 0.02272817933311065,
"max": 0.06495000508924326,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18504652865231036,
"min": 0.0454563586662213,
"max": 0.18936279341578482,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.65414878198333e-06,
"min": 3.65414878198333e-06,
"max": 0.00029536087654637497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.096244634594999e-05,
"min": 1.096244634594999e-05,
"max": 0.0008443275185574999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012180166666667,
"min": 0.1012180166666667,
"max": 0.19845362500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036540500000001,
"min": 0.20757004999999995,
"max": 0.5814425000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.077903166666665e-05,
"min": 7.077903166666665e-05,
"max": 0.004922835887499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021233709499999997,
"min": 0.00021233709499999997,
"max": 0.014073980749999998,
"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": "1734561956",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734564539"
},
"total": 2583.74765106,
"count": 1,
"self": 0.7125494500000968,
"children": {
"run_training.setup": {
"total": 0.06598692500000425,
"count": 1,
"self": 0.06598692500000425
},
"TrainerController.start_learning": {
"total": 2582.969114685,
"count": 1,
"self": 4.704244724061937,
"children": {
"TrainerController._reset_env": {
"total": 4.850292259000014,
"count": 1,
"self": 4.850292259000014
},
"TrainerController.advance": {
"total": 2573.247138803938,
"count": 232096,
"self": 4.810473879957499,
"children": {
"env_step": {
"total": 2025.4721162269743,
"count": 232096,
"self": 1590.8985499208356,
"children": {
"SubprocessEnvManager._take_step": {
"total": 431.5919137030807,
"count": 232096,
"self": 16.371350143032828,
"children": {
"TorchPolicy.evaluate": {
"total": 415.2205635600479,
"count": 222935,
"self": 415.2205635600479
}
}
},
"workers": {
"total": 2.9816526030580803,
"count": 232096,
"self": 0.0,
"children": {
"worker_root": {
"total": 2575.374537266894,
"count": 232096,
"is_parallel": true,
"self": 1285.3629119798989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008506769999598873,
"count": 1,
"is_parallel": true,
"self": 0.0002830409999319272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005676360000279601,
"count": 2,
"is_parallel": true,
"self": 0.0005676360000279601
}
}
},
"UnityEnvironment.step": {
"total": 0.03027885800003105,
"count": 1,
"is_parallel": true,
"self": 0.00035106899997572327,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019825800001171956,
"count": 1,
"is_parallel": true,
"self": 0.00019825800001171956
},
"communicator.exchange": {
"total": 0.028999042000009467,
"count": 1,
"is_parallel": true,
"self": 0.028999042000009467
},
"steps_from_proto": {
"total": 0.0007304890000341402,
"count": 1,
"is_parallel": true,
"self": 0.00019674100002475825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005337480000093819,
"count": 2,
"is_parallel": true,
"self": 0.0005337480000093819
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1290.0116252869952,
"count": 232095,
"is_parallel": true,
"self": 37.94105768585041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.62233404203698,
"count": 232095,
"is_parallel": true,
"self": 85.62233404203698
},
"communicator.exchange": {
"total": 1074.9030414700542,
"count": 232095,
"is_parallel": true,
"self": 1074.9030414700542
},
"steps_from_proto": {
"total": 91.54519208905356,
"count": 232095,
"is_parallel": true,
"self": 34.644717505020935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.90047458403262,
"count": 464190,
"is_parallel": true,
"self": 56.90047458403262
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 542.9645486970062,
"count": 232096,
"self": 6.879962312044881,
"children": {
"process_trajectory": {
"total": 178.34342952196232,
"count": 232096,
"self": 176.91474755196145,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4286819700008664,
"count": 10,
"self": 1.4286819700008664
}
}
},
"_update_policy": {
"total": 357.741156862999,
"count": 97,
"self": 288.30904101700406,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.43211584599493,
"count": 2910,
"self": 69.43211584599493
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2790001164830755e-06,
"count": 1,
"self": 1.2790001164830755e-06
},
"TrainerController._save_models": {
"total": 0.16743761899988385,
"count": 1,
"self": 0.0031808779999664694,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16425674099991738,
"count": 1,
"self": 0.16425674099991738
}
}
}
}
}
}
}