ppo-Huggy / run_logs /timers.json
Max87152's picture
Huggy
794a2fc verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046467542648315,
"min": 1.4046467542648315,
"max": 1.4254413843154907,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72257.8359375,
"min": 67669.078125,
"max": 78058.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.2778761061947,
"min": 81.71688741721854,
"max": 404.136,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49312.0,
"min": 48692.0,
"max": 50517.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49892.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49892.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4602789878845215,
"min": 0.09833568334579468,
"max": 2.473654270172119,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1392.5179443359375,
"min": 12.193624496459961,
"max": 1451.1885986328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8356894575875553,
"min": 1.7672797711866517,
"max": 3.958888236284256,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2171.0002329945564,
"min": 219.1426916271448,
"max": 2290.6348066329956,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8356894575875553,
"min": 1.7672797711866517,
"max": 3.958888236284256,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2171.0002329945564,
"min": 219.1426916271448,
"max": 2290.6348066329956,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018000946661858405,
"min": 0.013687232542724814,
"max": 0.021011510302196258,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054002839985575216,
"min": 0.027374465085449627,
"max": 0.059664898433402405,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05578007362782955,
"min": 0.021165747133394083,
"max": 0.05875463945170243,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16734022088348866,
"min": 0.042331494266788165,
"max": 0.1762639183551073,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4457488514499996e-06,
"min": 3.4457488514499996e-06,
"max": 0.00029534235155255007,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0337246554349998e-05,
"min": 1.0337246554349998e-05,
"max": 0.0008443035185654998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114855,
"min": 0.10114855,
"max": 0.19844744999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344565,
"min": 0.2074235000000001,
"max": 0.5814345,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.731264500000002e-05,
"min": 6.731264500000002e-05,
"max": 0.0049225277549999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020193793500000007,
"min": 0.00020193793500000007,
"max": 0.014073581550000002,
"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": "1714654142",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714656606"
},
"total": 2463.808855859,
"count": 1,
"self": 0.43981020199998966,
"children": {
"run_training.setup": {
"total": 0.055408505000002606,
"count": 1,
"self": 0.055408505000002606
},
"TrainerController.start_learning": {
"total": 2463.313637152,
"count": 1,
"self": 4.35961718200997,
"children": {
"TrainerController._reset_env": {
"total": 2.7181834860000436,
"count": 1,
"self": 2.7181834860000436
},
"TrainerController.advance": {
"total": 2456.10869357599,
"count": 232507,
"self": 4.7765663560271605,
"children": {
"env_step": {
"total": 1975.2206242930224,
"count": 232507,
"self": 1640.5748675269667,
"children": {
"SubprocessEnvManager._take_step": {
"total": 331.598170906064,
"count": 232507,
"self": 16.87695072116054,
"children": {
"TorchPolicy.evaluate": {
"total": 314.7212201849035,
"count": 223070,
"self": 314.7212201849035
}
}
},
"workers": {
"total": 3.0475858599916705,
"count": 232507,
"self": 0.0,
"children": {
"worker_root": {
"total": 2456.1045347159475,
"count": 232507,
"is_parallel": true,
"self": 1135.0291858999371,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009078470000076777,
"count": 1,
"is_parallel": true,
"self": 0.0002554550000013478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006523920000063299,
"count": 2,
"is_parallel": true,
"self": 0.0006523920000063299
}
}
},
"UnityEnvironment.step": {
"total": 0.030742062000001624,
"count": 1,
"is_parallel": true,
"self": 0.00041909800000894393,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021031599999332684,
"count": 1,
"is_parallel": true,
"self": 0.00021031599999332684
},
"communicator.exchange": {
"total": 0.029281781000008777,
"count": 1,
"is_parallel": true,
"self": 0.029281781000008777
},
"steps_from_proto": {
"total": 0.000830866999990576,
"count": 1,
"is_parallel": true,
"self": 0.0002189229999771669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006119440000134091,
"count": 2,
"is_parallel": true,
"self": 0.0006119440000134091
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1321.0753488160103,
"count": 232506,
"is_parallel": true,
"self": 39.86138399596189,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.12776731801557,
"count": 232506,
"is_parallel": true,
"self": 87.12776731801557
},
"communicator.exchange": {
"total": 1099.99791994205,
"count": 232506,
"is_parallel": true,
"self": 1099.99791994205
},
"steps_from_proto": {
"total": 94.08827755998271,
"count": 232506,
"is_parallel": true,
"self": 35.60652307791412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.481754482068595,
"count": 465012,
"is_parallel": true,
"self": 58.481754482068595
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.1115029269403,
"count": 232507,
"self": 6.5243562330001055,
"children": {
"process_trajectory": {
"total": 163.0336991419402,
"count": 232507,
"self": 161.67385161994042,
"children": {
"RLTrainer._checkpoint": {
"total": 1.359847521999768,
"count": 10,
"self": 1.359847521999768
}
}
},
"_update_policy": {
"total": 306.553447552,
"count": 97,
"self": 245.4343648369969,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.11908271500312,
"count": 2910,
"self": 61.11908271500312
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1100000847363845e-06,
"count": 1,
"self": 1.1100000847363845e-06
},
"TrainerController._save_models": {
"total": 0.1271417980001388,
"count": 1,
"self": 0.001955015000021376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12518678300011743,
"count": 1,
"self": 0.12518678300011743
}
}
}
}
}
}
}