ppo-Pyramids / run_logs /timers.json
goforit123's picture
First Push
784883e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3786891996860504,
"min": 0.3786891996860504,
"max": 1.4370561838150024,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11360.67578125,
"min": 11360.67578125,
"max": 43594.53515625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989882.0,
"min": 29923.0,
"max": 989882.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989882.0,
"min": 29923.0,
"max": 989882.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4638705253601074,
"min": -0.11470931023359299,
"max": 0.5302190184593201,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 127.56439208984375,
"min": -27.30081558227539,
"max": 147.40089416503906,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.020136507228016853,
"min": -0.003700815374031663,
"max": 0.3939352035522461,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.537539482116699,
"min": -0.9585111737251282,
"max": 93.75657653808594,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07238542809759059,
"min": 0.06612573949356318,
"max": 0.07379466588335003,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0857814214638588,
"min": 0.48219978384273504,
"max": 1.0857814214638588,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01563808350765612,
"min": 0.0004905543569347213,
"max": 0.016210765125126474,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2345712526148418,
"min": 0.005886652283216655,
"max": 0.24316147687689713,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.457137514320004e-06,
"min": 7.457137514320004e-06,
"max": 0.0002952341587314714,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011185706271480005,
"min": 0.00011185706271480005,
"max": 0.0033326292891235998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248568,
"min": 0.10248568,
"max": 0.1984113857142857,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372852,
"min": 1.3888797,
"max": 2.4850872,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025831943200000014,
"min": 0.00025831943200000014,
"max": 0.009841297432857141,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003874791480000002,
"min": 0.003874791480000002,
"max": 0.11109655236,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010547298938035965,
"min": 0.010547298938035965,
"max": 0.3958170711994171,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15820948779582977,
"min": 0.14953772723674774,
"max": 2.770719528198242,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 369.0470588235294,
"min": 361.57142857142856,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31369.0,
"min": 17105.0,
"max": 33578.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.489729399716153,
"min": -0.9998667180538178,
"max": 1.6166140963049496,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 126.626998975873,
"min": -29.996001541614532,
"max": 137.41219818592072,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.489729399716153,
"min": -0.9998667180538178,
"max": 1.6166140963049496,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 126.626998975873,
"min": -29.996001541614532,
"max": 137.41219818592072,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.040136543362271314,
"min": 0.040136543362271314,
"max": 7.583531709594859,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.4116061857930617,
"min": 3.261393619439332,
"max": 136.50357077270746,
"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": "1763464944",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ../config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1763466582"
},
"total": 1637.965888548999,
"count": 1,
"self": 0.32289034299901687,
"children": {
"run_training.setup": {
"total": 0.023227207000672934,
"count": 1,
"self": 0.023227207000672934
},
"TrainerController.start_learning": {
"total": 1637.6197709989992,
"count": 1,
"self": 1.2392014240467688,
"children": {
"TrainerController._reset_env": {
"total": 2.188091283000176,
"count": 1,
"self": 2.188091283000176
},
"TrainerController.advance": {
"total": 1634.1198416579518,
"count": 63710,
"self": 1.2013521441531338,
"children": {
"env_step": {
"total": 1012.6405566170597,
"count": 63710,
"self": 874.6161829811335,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.29222151701833,
"count": 63710,
"self": 4.118207000763505,
"children": {
"TorchPolicy.evaluate": {
"total": 133.17401451625483,
"count": 62566,
"self": 133.17401451625483
}
}
},
"workers": {
"total": 0.7321521189078339,
"count": 63710,
"self": 0.0,
"children": {
"worker_root": {
"total": 1635.4184336702328,
"count": 63710,
"is_parallel": true,
"self": 847.2096214310623,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018265380003867904,
"count": 1,
"is_parallel": true,
"self": 0.0006070410017855465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012194969986012438,
"count": 8,
"is_parallel": true,
"self": 0.0012194969986012438
}
}
},
"UnityEnvironment.step": {
"total": 0.03624751799907244,
"count": 1,
"is_parallel": true,
"self": 0.0003481819985609036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002898520015151007,
"count": 1,
"is_parallel": true,
"self": 0.0002898520015151007
},
"communicator.exchange": {
"total": 0.03457718999925419,
"count": 1,
"is_parallel": true,
"self": 0.03457718999925419
},
"steps_from_proto": {
"total": 0.0010322939997422509,
"count": 1,
"is_parallel": true,
"self": 0.00023846400290494785,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000793829996837303,
"count": 8,
"is_parallel": true,
"self": 0.000793829996837303
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 788.2088122391706,
"count": 63709,
"is_parallel": true,
"self": 19.20063503860365,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.330939972873239,
"count": 63709,
"is_parallel": true,
"self": 13.330939972873239
},
"communicator.exchange": {
"total": 698.2680461969594,
"count": 63709,
"is_parallel": true,
"self": 698.2680461969594
},
"steps_from_proto": {
"total": 57.40919103073429,
"count": 63709,
"is_parallel": true,
"self": 12.087800972012701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 45.32139005872159,
"count": 509672,
"is_parallel": true,
"self": 45.32139005872159
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 620.277932896739,
"count": 63710,
"self": 2.3753198085305485,
"children": {
"process_trajectory": {
"total": 113.58270773722325,
"count": 63710,
"self": 113.4028764192226,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17983131800065166,
"count": 2,
"self": 0.17983131800065166
}
}
},
"_update_policy": {
"total": 504.3199053509852,
"count": 451,
"self": 278.18168818926824,
"children": {
"TorchPPOOptimizer.update": {
"total": 226.13821716171697,
"count": 22788,
"self": 226.13821716171697
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.07263560600040364,
"count": 1,
"self": 0.0010048090007330757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07163079699967057,
"count": 1,
"self": 0.07163079699967057
}
}
}
}
}
}
}