ppo-Huggy / run_logs /timers.json
wendyl21's picture
Huggy
deb9e1d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053428173065186,
"min": 1.4053428173065186,
"max": 1.4277582168579102,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70930.4609375,
"min": 68442.125,
"max": 78062.6875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.04545454545455,
"min": 81.38220757825371,
"max": 389.1860465116279,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50075.0,
"min": 49314.0,
"max": 50205.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999904.0,
"min": 49714.0,
"max": 1999904.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999904.0,
"min": 49714.0,
"max": 1999904.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3993914127349854,
"min": 0.09190163761377335,
"max": 2.4334731101989746,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1319.665283203125,
"min": 11.763409614562988,
"max": 1463.7841796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.737978015054356,
"min": 1.8242881568148732,
"max": 3.964188722595004,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2055.887908279896,
"min": 233.50888407230377,
"max": 2346.7478976249695,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.737978015054356,
"min": 1.8242881568148732,
"max": 3.964188722595004,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2055.887908279896,
"min": 233.50888407230377,
"max": 2346.7478976249695,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01709775768071672,
"min": 0.011962355181357352,
"max": 0.01988487830288553,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05129327304215016,
"min": 0.027316126711472558,
"max": 0.05921016401262023,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05467576281064087,
"min": 0.023053682347138723,
"max": 0.058218312449753284,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1640272884319226,
"min": 0.046107364694277446,
"max": 0.17101723874608676,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5172488276166685e-06,
"min": 3.5172488276166685e-06,
"max": 0.00029530305156564993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0551746482850005e-05,
"min": 1.0551746482850005e-05,
"max": 0.00084353716882095,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117238333333334,
"min": 0.10117238333333334,
"max": 0.1984343500000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30351715,
"min": 0.20747190000000007,
"max": 0.5811790500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.850192833333337e-05,
"min": 6.850192833333337e-05,
"max": 0.004921874065,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020550578500000012,
"min": 0.00020550578500000012,
"max": 0.014060834595000002,
"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": "1744635806",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744638264"
},
"total": 2457.534478894,
"count": 1,
"self": 0.488550017000307,
"children": {
"run_training.setup": {
"total": 0.023573242999987087,
"count": 1,
"self": 0.023573242999987087
},
"TrainerController.start_learning": {
"total": 2457.0223556339997,
"count": 1,
"self": 4.2412397698872155,
"children": {
"TrainerController._reset_env": {
"total": 3.1468436060000613,
"count": 1,
"self": 3.1468436060000613
},
"TrainerController.advance": {
"total": 2449.5143235931127,
"count": 232191,
"self": 4.438173895165164,
"children": {
"env_step": {
"total": 1943.1050059689564,
"count": 232191,
"self": 1526.555436795893,
"children": {
"SubprocessEnvManager._take_step": {
"total": 413.86406992699256,
"count": 232191,
"self": 15.786834643977954,
"children": {
"TorchPolicy.evaluate": {
"total": 398.0772352830146,
"count": 222970,
"self": 398.0772352830146
}
}
},
"workers": {
"total": 2.6854992460707763,
"count": 232191,
"self": 0.0,
"children": {
"worker_root": {
"total": 2449.872583534008,
"count": 232191,
"is_parallel": true,
"self": 1203.7252856281302,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010667689999763752,
"count": 1,
"is_parallel": true,
"self": 0.0003951000001052307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006716689998711445,
"count": 2,
"is_parallel": true,
"self": 0.0006716689998711445
}
}
},
"UnityEnvironment.step": {
"total": 0.03066719099990678,
"count": 1,
"is_parallel": true,
"self": 0.0003260829998907866,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021338099998047255,
"count": 1,
"is_parallel": true,
"self": 0.00021338099998047255
},
"communicator.exchange": {
"total": 0.029381222999973033,
"count": 1,
"is_parallel": true,
"self": 0.029381222999973033
},
"steps_from_proto": {
"total": 0.0007465040000624867,
"count": 1,
"is_parallel": true,
"self": 0.0002131730001337928,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005333309999286939,
"count": 2,
"is_parallel": true,
"self": 0.0005333309999286939
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1246.1472979058776,
"count": 232190,
"is_parallel": true,
"self": 37.79471718599439,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.60777656498499,
"count": 232190,
"is_parallel": true,
"self": 80.60777656498499
},
"communicator.exchange": {
"total": 1040.528156246945,
"count": 232190,
"is_parallel": true,
"self": 1040.528156246945
},
"steps_from_proto": {
"total": 87.2166479079533,
"count": 232190,
"is_parallel": true,
"self": 30.591444150870075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.62520375708323,
"count": 464380,
"is_parallel": true,
"self": 56.62520375708323
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.97114372899114,
"count": 232191,
"self": 6.7015208510738375,
"children": {
"process_trajectory": {
"total": 166.02427635791707,
"count": 232191,
"self": 164.7611398619183,
"children": {
"RLTrainer._checkpoint": {
"total": 1.263136495998765,
"count": 10,
"self": 1.263136495998765
}
}
},
"_update_policy": {
"total": 329.2453465200002,
"count": 97,
"self": 263.2791915969801,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.9661549230201,
"count": 2910,
"self": 65.9661549230201
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.420000424142927e-07,
"count": 1,
"self": 9.420000424142927e-07
},
"TrainerController._save_models": {
"total": 0.1199477229997683,
"count": 1,
"self": 0.0019512399999257468,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11799648299984256,
"count": 1,
"self": 0.11799648299984256
}
}
}
}
}
}
}