ppo-Huggy / run_logs /timers.json
costazd's picture
Huggy
aee07a4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4018937349319458,
"min": 1.4018937349319458,
"max": 1.4263609647750854,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69074.109375,
"min": 68332.90625,
"max": 76299.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.41929133858268,
"min": 94.50095602294455,
"max": 381.8702290076336,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49489.0,
"min": 48887.0,
"max": 50294.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49910.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49910.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3421804904937744,
"min": 0.05784738436341286,
"max": 2.4009861946105957,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1189.82763671875,
"min": 7.52016019821167,
"max": 1222.2626953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.588005329562923,
"min": 1.8258946335086457,
"max": 3.8422746645469292,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1822.706707417965,
"min": 237.36630235612392,
"max": 1959.5600789189339,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.588005329562923,
"min": 1.8258946335086457,
"max": 3.8422746645469292,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1822.706707417965,
"min": 237.36630235612392,
"max": 1959.5600789189339,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015129938162678198,
"min": 0.012776695641999444,
"max": 0.01972894055506913,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04538981448803459,
"min": 0.02555339128399889,
"max": 0.05766704059205949,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05224537129203479,
"min": 0.024251209168384472,
"max": 0.05742650768823093,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15673611387610437,
"min": 0.048502418336768945,
"max": 0.1722795230646928,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1058989647333355e-06,
"min": 3.1058989647333355e-06,
"max": 0.0002953075515641499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.317696894200007e-06,
"min": 9.317696894200007e-06,
"max": 0.0008438142187285998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10103526666666666,
"min": 0.10103526666666666,
"max": 0.19843585000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031058,
"min": 0.20720264999999993,
"max": 0.5812714000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.165980666666672e-05,
"min": 6.165980666666672e-05,
"max": 0.004921948914999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018497942000000016,
"min": 0.00018497942000000016,
"max": 0.01406544286,
"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": "1710921078",
"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": "1710923661"
},
"total": 2582.392969974,
"count": 1,
"self": 0.4390274999996109,
"children": {
"run_training.setup": {
"total": 0.08866642100002764,
"count": 1,
"self": 0.08866642100002764
},
"TrainerController.start_learning": {
"total": 2581.8652760530003,
"count": 1,
"self": 4.723102515032224,
"children": {
"TrainerController._reset_env": {
"total": 3.2558191759999886,
"count": 1,
"self": 3.2558191759999886
},
"TrainerController.advance": {
"total": 2573.767389530968,
"count": 231440,
"self": 4.941196257020238,
"children": {
"env_step": {
"total": 2074.3558134849454,
"count": 231440,
"self": 1718.5846568349066,
"children": {
"SubprocessEnvManager._take_step": {
"total": 352.5771444089977,
"count": 231440,
"self": 19.490390552922292,
"children": {
"TorchPolicy.evaluate": {
"total": 333.0867538560754,
"count": 222918,
"self": 333.0867538560754
}
}
},
"workers": {
"total": 3.1940122410411504,
"count": 231440,
"self": 0.0,
"children": {
"worker_root": {
"total": 2574.312146369018,
"count": 231440,
"is_parallel": true,
"self": 1191.599497829058,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012648259999537004,
"count": 1,
"is_parallel": true,
"self": 0.0004002499999273823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008645760000263181,
"count": 2,
"is_parallel": true,
"self": 0.0008645760000263181
}
}
},
"UnityEnvironment.step": {
"total": 0.03077673100000311,
"count": 1,
"is_parallel": true,
"self": 0.00039365499998211817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001967950000221208,
"count": 1,
"is_parallel": true,
"self": 0.0001967950000221208
},
"communicator.exchange": {
"total": 0.029432831000008264,
"count": 1,
"is_parallel": true,
"self": 0.029432831000008264
},
"steps_from_proto": {
"total": 0.0007534499999906075,
"count": 1,
"is_parallel": true,
"self": 0.0002148689999899034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005385810000007041,
"count": 2,
"is_parallel": true,
"self": 0.0005385810000007041
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1382.7126485399601,
"count": 231439,
"is_parallel": true,
"self": 41.66766355791515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.01644410603086,
"count": 231439,
"is_parallel": true,
"self": 92.01644410603086
},
"communicator.exchange": {
"total": 1149.5129372880076,
"count": 231439,
"is_parallel": true,
"self": 1149.5129372880076
},
"steps_from_proto": {
"total": 99.51560358800651,
"count": 231439,
"is_parallel": true,
"self": 37.8004212309969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.71518235700961,
"count": 462878,
"is_parallel": true,
"self": 61.71518235700961
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.4703797890024,
"count": 231440,
"self": 7.422469443941225,
"children": {
"process_trajectory": {
"total": 162.67668162406244,
"count": 231440,
"self": 161.30341243906275,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3732691849996854,
"count": 10,
"self": 1.3732691849996854
}
}
},
"_update_policy": {
"total": 324.3712287209987,
"count": 97,
"self": 260.52303241300126,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.848196307997455,
"count": 2910,
"self": 63.848196307997455
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0170001587539446e-06,
"count": 1,
"self": 1.0170001587539446e-06
},
"TrainerController._save_models": {
"total": 0.11896381399992606,
"count": 1,
"self": 0.0020603319999281666,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1169034819999979,
"count": 1,
"self": 0.1169034819999979
}
}
}
}
}
}
}