ppo-Huggy / run_logs /timers.json
saamur's picture
Huggy
758a952 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100295305252075,
"min": 1.4100295305252075,
"max": 1.4290032386779785,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70889.234375,
"min": 67696.5,
"max": 78125.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.27160493827161,
"min": 76.27160493827161,
"max": 379.93939393939394,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49424.0,
"min": 49128.0,
"max": 50152.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999930.0,
"min": 49880.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999930.0,
"min": 49880.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4170987606048584,
"min": 0.1247144490480423,
"max": 2.5281827449798584,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1566.280029296875,
"min": 16.33759307861328,
"max": 1566.280029296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7251844505469003,
"min": 1.7093278599604396,
"max": 4.046901326499829,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2413.9195239543915,
"min": 223.92194965481758,
"max": 2490.2912263274193,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7251844505469003,
"min": 1.7093278599604396,
"max": 4.046901326499829,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2413.9195239543915,
"min": 223.92194965481758,
"max": 2490.2912263274193,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020254919197355375,
"min": 0.01322963655438798,
"max": 0.020254919197355375,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06076475759206612,
"min": 0.02645927310877596,
"max": 0.06076475759206612,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05794305917289522,
"min": 0.023133155517280103,
"max": 0.05810092315077782,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17382917751868565,
"min": 0.046266311034560206,
"max": 0.17382917751868565,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.688398770566665e-06,
"min": 3.688398770566665e-06,
"max": 0.000295277176574275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1065196311699996e-05,
"min": 1.1065196311699996e-05,
"max": 0.0008440111686629499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122943333333333,
"min": 0.10122943333333333,
"max": 0.198425725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30368829999999997,
"min": 0.20760614999999993,
"max": 0.5813370499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.134872333333334e-05,
"min": 7.134872333333334e-05,
"max": 0.0049214436775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021404617000000004,
"min": 0.00021404617000000004,
"max": 0.014068718795,
"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": "1728941054",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728943642"
},
"total": 2587.807371424,
"count": 1,
"self": 0.4294167670000206,
"children": {
"run_training.setup": {
"total": 0.07967641900006583,
"count": 1,
"self": 0.07967641900006583
},
"TrainerController.start_learning": {
"total": 2587.298278238,
"count": 1,
"self": 4.651047960082451,
"children": {
"TrainerController._reset_env": {
"total": 4.691424052000002,
"count": 1,
"self": 4.691424052000002
},
"TrainerController.advance": {
"total": 2577.8353012439175,
"count": 233305,
"self": 4.94455045498853,
"children": {
"env_step": {
"total": 2045.3132058949377,
"count": 233305,
"self": 1610.1691666489373,
"children": {
"SubprocessEnvManager._take_step": {
"total": 432.1226829100018,
"count": 233305,
"self": 16.479155012104002,
"children": {
"TorchPolicy.evaluate": {
"total": 415.6435278978978,
"count": 222996,
"self": 415.6435278978978
}
}
},
"workers": {
"total": 3.021356335998462,
"count": 233305,
"self": 0.0,
"children": {
"worker_root": {
"total": 2579.711498950001,
"count": 233305,
"is_parallel": true,
"self": 1281.1528440479979,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011337060000187194,
"count": 1,
"is_parallel": true,
"self": 0.00033808299997417635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000795623000044543,
"count": 2,
"is_parallel": true,
"self": 0.000795623000044543
}
}
},
"UnityEnvironment.step": {
"total": 0.03161699100007809,
"count": 1,
"is_parallel": true,
"self": 0.00040237500013518,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021507899998596258,
"count": 1,
"is_parallel": true,
"self": 0.00021507899998596258
},
"communicator.exchange": {
"total": 0.030214688999990358,
"count": 1,
"is_parallel": true,
"self": 0.030214688999990358
},
"steps_from_proto": {
"total": 0.0007848479999665869,
"count": 1,
"is_parallel": true,
"self": 0.00022006100005000917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005647869999165778,
"count": 2,
"is_parallel": true,
"self": 0.0005647869999165778
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.5586549020031,
"count": 233304,
"is_parallel": true,
"self": 39.889198311124574,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.51406753685126,
"count": 233304,
"is_parallel": true,
"self": 86.51406753685126
},
"communicator.exchange": {
"total": 1078.9762485000438,
"count": 233304,
"is_parallel": true,
"self": 1078.9762485000438
},
"steps_from_proto": {
"total": 93.17914055398364,
"count": 233304,
"is_parallel": true,
"self": 35.71907199204168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.460068561941966,
"count": 466608,
"is_parallel": true,
"self": 57.460068561941966
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.577544893991,
"count": 233305,
"self": 6.683747249995804,
"children": {
"process_trajectory": {
"total": 173.18703852899466,
"count": 233305,
"self": 171.79595043999495,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3910880889997088,
"count": 10,
"self": 1.3910880889997088
}
}
},
"_update_policy": {
"total": 347.7067591150005,
"count": 97,
"self": 281.31824015401014,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.38851896099038,
"count": 2910,
"self": 66.38851896099038
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.190000148199033e-06,
"count": 1,
"self": 1.190000148199033e-06
},
"TrainerController._save_models": {
"total": 0.12050379199990857,
"count": 1,
"self": 0.0018118439998033864,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11869194800010519,
"count": 1,
"self": 0.11869194800010519
}
}
}
}
}
}
}