ppo-Pyramids / run_logs /timers.json
wooii's picture
First Push
8cb24f3
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.413578987121582,
"min": 1.397755742073059,
"max": 1.6056334972381592,
"count": 20
},
"Pyramids.Policy.Entropy.sum": {
"value": 12823.98828125,
"min": 12823.98828125,
"max": 17328.921875,
"count": 20
},
"Pyramids.Step.mean": {
"value": 199986.0,
"min": 9984.0,
"max": 199986.0,
"count": 20
},
"Pyramids.Step.sum": {
"value": 199986.0,
"min": 9984.0,
"max": 199986.0,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0929415225982666,
"min": -0.11384790390729904,
"max": -0.07797608524560928,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -15.056526184082031,
"min": -17.760272979736328,
"max": -12.596552848815918,
"count": 20
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06743357254712017,
"min": 0.062215721632431574,
"max": 0.07811797409936133,
"count": 20
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.26973429018848066,
"min": 0.20927058210523397,
"max": 0.34798694200281083,
"count": 20
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 8.091830123172865e-05,
"min": 7.701856860591391e-05,
"max": 0.004301159609832281,
"count": 20
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0003236732049269146,
"min": 0.00030807427442365565,
"max": 0.012903478829496842,
"count": 20
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.521097493000002e-06,
"min": 7.521097493000002e-06,
"max": 0.00029222400259199996,
"count": 20
},
"Pyramids.Policy.LearningRate.sum": {
"value": 3.0084389972000007e-05,
"min": 3.0084389972000007e-05,
"max": 0.001114152028616,
"count": 20
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.102507,
"min": 0.102507,
"max": 0.19740800000000003,
"count": 20
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.410028,
"min": 0.410028,
"max": 0.771384,
"count": 20
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00013509930000000006,
"min": 0.00013509930000000006,
"max": 0.0048706592,
"count": 20
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0005403972000000003,
"min": 0.0005403972000000003,
"max": 0.018572061600000002,
"count": 20
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 547.0,
"max": 999.0,
"count": 18
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 13986.0,
"min": 547.0,
"max": 15984.0,
"count": 18
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000447034836,
"min": -1.0000000447034836,
"max": 1.453000009059906,
"count": 18
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -14.00000062584877,
"min": -16.000000715255737,
"max": 1.453000009059906,
"count": 18
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000447034836,
"min": -1.0000000447034836,
"max": 1.453000009059906,
"count": 18
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -14.00000062584877,
"min": -16.000000715255737,
"max": 1.453000009059906,
"count": 18
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1696418264",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo1.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1696418645"
},
"total": 380.9887927320001,
"count": 1,
"self": 0.47470508700030223,
"children": {
"run_training.setup": {
"total": 0.04158787099981964,
"count": 1,
"self": 0.04158787099981964
},
"TrainerController.start_learning": {
"total": 380.47249977399997,
"count": 1,
"self": 0.4405940579936214,
"children": {
"TrainerController._reset_env": {
"total": 3.9424662469998566,
"count": 1,
"self": 3.9424662469998566
},
"TrainerController.advance": {
"total": 376.0085436330062,
"count": 12541,
"self": 0.22320526106636862,
"children": {
"env_step": {
"total": 375.7853383719398,
"count": 12541,
"self": 301.4556541349243,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.10809485601317,
"count": 12541,
"self": 1.217982551017485,
"children": {
"TorchPolicy.evaluate": {
"total": 72.89011230499568,
"count": 12532,
"self": 72.89011230499568
}
}
},
"workers": {
"total": 0.22158938100233172,
"count": 12541,
"self": 0.0,
"children": {
"worker_root": {
"total": 379.2617054839661,
"count": 12541,
"is_parallel": true,
"self": 146.30666000995166,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004990541000097437,
"count": 1,
"is_parallel": true,
"self": 0.0031850640002630826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018054769998343545,
"count": 8,
"is_parallel": true,
"self": 0.0018054769998343545
}
}
},
"UnityEnvironment.step": {
"total": 0.05316238099999282,
"count": 1,
"is_parallel": true,
"self": 0.0005587969999396591,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005122700001720659,
"count": 1,
"is_parallel": true,
"self": 0.0005122700001720659
},
"communicator.exchange": {
"total": 0.04888151799991647,
"count": 1,
"is_parallel": true,
"self": 0.04888151799991647
},
"steps_from_proto": {
"total": 0.0032097959999646264,
"count": 1,
"is_parallel": true,
"self": 0.00044106599989390816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027687300000707182,
"count": 8,
"is_parallel": true,
"self": 0.0027687300000707182
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.95504547401447,
"count": 12540,
"is_parallel": true,
"self": 7.09552791801184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.030593728983376,
"count": 12540,
"is_parallel": true,
"self": 5.030593728983376
},
"communicator.exchange": {
"total": 197.07278988501525,
"count": 12540,
"is_parallel": true,
"self": 197.07278988501525
},
"steps_from_proto": {
"total": 23.756133942004,
"count": 12540,
"is_parallel": true,
"self": 4.905456346073606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.850677595930392,
"count": 100320,
"is_parallel": true,
"self": 18.850677595930392
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019236500020269887,
"count": 1,
"self": 0.00019236500020269887,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 374.91485283604106,
"count": 162899,
"is_parallel": true,
"self": 3.745572844065464,
"children": {
"process_trajectory": {
"total": 136.83645773697594,
"count": 162899,
"is_parallel": true,
"self": 136.24651712697573,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5899406100002125,
"count": 4,
"is_parallel": true,
"self": 0.5899406100002125
}
}
},
"_update_policy": {
"total": 234.33282225499966,
"count": 80,
"is_parallel": true,
"self": 89.0253891780028,
"children": {
"TorchPPOOptimizer.update": {
"total": 145.30743307699686,
"count": 4557,
"is_parallel": true,
"self": 145.30743307699686
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08070347100010622,
"count": 1,
"self": 0.0007366869999714254,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0799667840001348,
"count": 1,
"self": 0.0799667840001348
}
}
}
}
}
}
}