ppo-Huggy / run_logs /timers.json
Harri's picture
Huggy
cd63372
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4016517400741577,
"min": 1.401649832725525,
"max": 1.4280067682266235,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69939.6171875,
"min": 67946.3125,
"max": 77631.296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 70.41084165477889,
"min": 66.86684782608695,
"max": 387.5846153846154,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49358.0,
"min": 49214.0,
"max": 50386.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49766.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49766.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4985175132751465,
"min": 0.09042340517044067,
"max": 2.5276286602020264,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1751.4608154296875,
"min": 11.664619445800781,
"max": 1815.4970703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.906046535591256,
"min": 1.908694139284681,
"max": 4.109062134259928,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2738.1386214494705,
"min": 246.22154396772385,
"max": 2833.306886255741,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.906046535591256,
"min": 1.908694139284681,
"max": 4.109062134259928,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2738.1386214494705,
"min": 246.22154396772385,
"max": 2833.306886255741,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013484290900952246,
"min": 0.013251182240431566,
"max": 0.021368501845427088,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04045287270285674,
"min": 0.02650236448086313,
"max": 0.05893082893380779,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06477389021052254,
"min": 0.024167555694778763,
"max": 0.07227645640571911,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19432167063156763,
"min": 0.048335111389557525,
"max": 0.19432167063156763,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.1968986010666665e-06,
"min": 4.1968986010666665e-06,
"max": 0.00029537910154029995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.25906958032e-05,
"min": 1.25906958032e-05,
"max": 0.0008443552685482498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10139893333333334,
"min": 0.10139893333333334,
"max": 0.19845969999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30419680000000004,
"min": 0.20792780000000005,
"max": 0.5814517499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.980677333333337e-05,
"min": 7.980677333333337e-05,
"max": 0.004923139029999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023942032000000008,
"min": 0.00023942032000000008,
"max": 0.014074442325000004,
"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": "1671194542",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671196972"
},
"total": 2429.2073852599997,
"count": 1,
"self": 0.44338251799945283,
"children": {
"run_training.setup": {
"total": 0.11379957799999829,
"count": 1,
"self": 0.11379957799999829
},
"TrainerController.start_learning": {
"total": 2428.6502031640002,
"count": 1,
"self": 4.546341433941961,
"children": {
"TrainerController._reset_env": {
"total": 9.909112627000013,
"count": 1,
"self": 9.909112627000013
},
"TrainerController.advance": {
"total": 2414.0764130320586,
"count": 233610,
"self": 4.604577113028881,
"children": {
"env_step": {
"total": 1922.6598511180223,
"count": 233610,
"self": 1615.0534100181621,
"children": {
"SubprocessEnvManager._take_step": {
"total": 304.5975693109666,
"count": 233610,
"self": 16.08993306895468,
"children": {
"TorchPolicy.evaluate": {
"total": 288.5076362420119,
"count": 222921,
"self": 71.72378388990933,
"children": {
"TorchPolicy.sample_actions": {
"total": 216.7838523521026,
"count": 222921,
"self": 216.7838523521026
}
}
}
}
},
"workers": {
"total": 3.0088717888934298,
"count": 233610,
"self": 0.0,
"children": {
"worker_root": {
"total": 2419.676213581074,
"count": 233610,
"is_parallel": true,
"self": 1095.3247500969587,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0040660160000243195,
"count": 1,
"is_parallel": true,
"self": 0.00035722199993415416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0037087940000901654,
"count": 2,
"is_parallel": true,
"self": 0.0037087940000901654
}
}
},
"UnityEnvironment.step": {
"total": 0.029274332999989383,
"count": 1,
"is_parallel": true,
"self": 0.0002920320000612264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002189460000181498,
"count": 1,
"is_parallel": true,
"self": 0.0002189460000181498
},
"communicator.exchange": {
"total": 0.027953867999940485,
"count": 1,
"is_parallel": true,
"self": 0.027953867999940485
},
"steps_from_proto": {
"total": 0.000809486999969522,
"count": 1,
"is_parallel": true,
"self": 0.00027351200003522536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005359749999342966,
"count": 2,
"is_parallel": true,
"self": 0.0005359749999342966
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1324.3514634841154,
"count": 233609,
"is_parallel": true,
"self": 37.37398477917213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.08993367497794,
"count": 233609,
"is_parallel": true,
"self": 84.08993367497794
},
"communicator.exchange": {
"total": 1100.1003173429476,
"count": 233609,
"is_parallel": true,
"self": 1100.1003173429476
},
"steps_from_proto": {
"total": 102.78722768701755,
"count": 233609,
"is_parallel": true,
"self": 43.89791087794481,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.88931680907274,
"count": 467218,
"is_parallel": true,
"self": 58.88931680907274
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.8119848010075,
"count": 233610,
"self": 6.938304156013714,
"children": {
"process_trajectory": {
"total": 168.12308242499228,
"count": 233610,
"self": 166.92648002899227,
"children": {
"RLTrainer._checkpoint": {
"total": 1.196602396000003,
"count": 10,
"self": 1.196602396000003
}
}
},
"_update_policy": {
"total": 311.7505982200015,
"count": 97,
"self": 257.4632668880016,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.287331331999894,
"count": 2910,
"self": 54.287331331999894
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.679997674538754e-07,
"count": 1,
"self": 9.679997674538754e-07
},
"TrainerController._save_models": {
"total": 0.11833510299993577,
"count": 1,
"self": 0.002445277999868267,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1158898250000675,
"count": 1,
"self": 0.1158898250000675
}
}
}
}
}
}
}