Pyramids-ppo / run_logs /timers.json
PhilSad's picture
yoooo
70a95ee
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.37122392654418945,
"min": 0.37122392654418945,
"max": 1.5105650424957275,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11166.416015625,
"min": 11166.416015625,
"max": 45824.5,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989913.0,
"min": 29952.0,
"max": 989913.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989913.0,
"min": 29952.0,
"max": 989913.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5765018463134766,
"min": -0.06877413392066956,
"max": 0.6965348720550537,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 159.69100952148438,
"min": -16.643341064453125,
"max": 200.60205078125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0033404980786144733,
"min": -0.016246233135461807,
"max": 0.41353216767311096,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.9253179430961609,
"min": -4.402729034423828,
"max": 98.00712585449219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06696116397959283,
"min": 0.06464988897953713,
"max": 0.07363531251238394,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0044174596938924,
"min": 0.49453891861441823,
"max": 1.0768576345552563,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014878207167688137,
"min": 0.0014677261221524792,
"max": 0.01661062744378108,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22317310751532204,
"min": 0.017612713465829752,
"max": 0.23254878421293515,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.441137519653332e-06,
"min": 7.441137519653332e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011161706279479997,
"min": 0.00011161706279479997,
"max": 0.0036355288881571,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248034666666667,
"min": 0.10248034666666667,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372052,
"min": 1.3886848,
"max": 2.6118429000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257786632,
"min": 0.000257786632,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00386679948,
"min": 0.00386679948,
"max": 0.12120310571000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014334478415548801,
"min": 0.013930843211710453,
"max": 0.423235684633255,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.215017169713974,
"min": 0.1950318068265915,
"max": 2.9626498222351074,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 329.17241379310343,
"min": 279.27522935779814,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28638.0,
"min": 15984.0,
"max": 32756.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6248344594891044,
"min": -1.0000000521540642,
"max": 1.7023742894787308,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 141.36059797555208,
"min": -28.78800170123577,
"max": 185.55879755318165,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6248344594891044,
"min": -1.0000000521540642,
"max": 1.7023742894787308,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 141.36059797555208,
"min": -28.78800170123577,
"max": 185.55879755318165,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04956460634283936,
"min": 0.043109577023926184,
"max": 7.7357671381905675,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.312120751827024,
"min": 4.238870368106291,
"max": 123.77227421104908,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684342676",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --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": "1684345017"
},
"total": 2341.1863299710003,
"count": 1,
"self": 0.442237990000649,
"children": {
"run_training.setup": {
"total": 0.04076334000001225,
"count": 1,
"self": 0.04076334000001225
},
"TrainerController.start_learning": {
"total": 2340.7033286409996,
"count": 1,
"self": 1.4271199340473686,
"children": {
"TrainerController._reset_env": {
"total": 4.444754105000129,
"count": 1,
"self": 4.444754105000129
},
"TrainerController.advance": {
"total": 2334.7328580999524,
"count": 64110,
"self": 1.4593646570833698,
"children": {
"env_step": {
"total": 1675.03265021194,
"count": 64110,
"self": 1560.0390723089467,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.13799643598509,
"count": 64110,
"self": 5.104130318977241,
"children": {
"TorchPolicy.evaluate": {
"total": 109.03386611700785,
"count": 62572,
"self": 109.03386611700785
}
}
},
"workers": {
"total": 0.8555814670082782,
"count": 64110,
"self": 0.0,
"children": {
"worker_root": {
"total": 2335.051665194002,
"count": 64110,
"is_parallel": true,
"self": 896.4303108150418,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00767174700013129,
"count": 1,
"is_parallel": true,
"self": 0.0055491690006874705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00212257799944382,
"count": 8,
"is_parallel": true,
"self": 0.00212257799944382
}
}
},
"UnityEnvironment.step": {
"total": 0.09953938199987533,
"count": 1,
"is_parallel": true,
"self": 0.0006647010000051523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005197529999350081,
"count": 1,
"is_parallel": true,
"self": 0.0005197529999350081
},
"communicator.exchange": {
"total": 0.09630123500005539,
"count": 1,
"is_parallel": true,
"self": 0.09630123500005539
},
"steps_from_proto": {
"total": 0.002053692999879786,
"count": 1,
"is_parallel": true,
"self": 0.0004983269998319884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015553660000477976,
"count": 8,
"is_parallel": true,
"self": 0.0015553660000477976
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1438.6213543789602,
"count": 64109,
"is_parallel": true,
"self": 32.98454867695409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.82842116801862,
"count": 64109,
"is_parallel": true,
"self": 24.82842116801862
},
"communicator.exchange": {
"total": 1273.4046253749873,
"count": 64109,
"is_parallel": true,
"self": 1273.4046253749873
},
"steps_from_proto": {
"total": 107.40375915900017,
"count": 64109,
"is_parallel": true,
"self": 22.189547636126917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.21421152287326,
"count": 512872,
"is_parallel": true,
"self": 85.21421152287326
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 658.2408432309292,
"count": 64110,
"self": 2.7456755539103597,
"children": {
"process_trajectory": {
"total": 118.45038943302188,
"count": 64110,
"self": 118.21374936702159,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23664006600029097,
"count": 2,
"self": 0.23664006600029097
}
}
},
"_update_policy": {
"total": 537.0447782439969,
"count": 454,
"self": 348.433818702003,
"children": {
"TorchPPOOptimizer.update": {
"total": 188.6109595419939,
"count": 22743,
"self": 188.6109595419939
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1150000318593811e-06,
"count": 1,
"self": 1.1150000318593811e-06
},
"TrainerController._save_models": {
"total": 0.09859538699993209,
"count": 1,
"self": 0.0017207060000146157,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09687468099991747,
"count": 1,
"self": 0.09687468099991747
}
}
}
}
}
}
}