ppo-Pyramid3 / run_logs /timers.json
lipee's picture
awd
fc90295
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1879495084285736,
"min": 0.17651192843914032,
"max": 1.5151771306991577,
"count": 66
},
"Pyramids.Policy.Entropy.sum": {
"value": 5605.40625,
"min": 5312.81884765625,
"max": 45964.4140625,
"count": 66
},
"Pyramids.Step.mean": {
"value": 1979984.0,
"min": 29952.0,
"max": 1979984.0,
"count": 66
},
"Pyramids.Step.sum": {
"value": 1979984.0,
"min": 29952.0,
"max": 1979984.0,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7447231411933899,
"min": -0.13634398579597473,
"max": 0.8155695199966431,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 219.69332885742188,
"min": -32.85890197753906,
"max": 244.6708526611328,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0023275294806808233,
"min": -0.01113986223936081,
"max": 0.2555404305458069,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.6866211891174316,
"min": -3.2751195430755615,
"max": 60.563079833984375,
"count": 66
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06531711204184426,
"min": 0.06441993292170663,
"max": 0.07362295280772206,
"count": 66
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.979756680627664,
"min": 0.5048581532777378,
"max": 1.1009614725771826,
"count": 66
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015910970591034534,
"min": 0.0005704442670283412,
"max": 0.016257032085074265,
"count": 66
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23866455886551802,
"min": 0.005133998403255071,
"max": 0.2405631447715374,
"count": 66
},
"Pyramids.Policy.LearningRate.mean": {
"value": 6.964324925610001e-06,
"min": 6.964324925610001e-06,
"max": 0.00039676708652251427,
"count": 66
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010446487388415002,
"min": 0.00010446487388415002,
"max": 0.0051379769155057995,
"count": 66
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10174105666666669,
"min": 0.10174105666666669,
"max": 0.19919177142857142,
"count": 66
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5261158500000003,
"min": 1.3943424,
"max": 2.6961749,
"count": 66
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000183931561,
"min": 0.000183931561,
"max": 0.009919257965714285,
"count": 66
},
"Pyramids.Policy.Beta.sum": {
"value": 0.002758973415,
"min": 0.002758973415,
"max": 0.12846097058000003,
"count": 66
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006836412474513054,
"min": 0.006447747815400362,
"max": 0.3378683924674988,
"count": 66
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10254618525505066,
"min": 0.09077324718236923,
"max": 2.3650786876678467,
"count": 66
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 246.77777777777777,
"min": 227.65853658536585,
"max": 999.0,
"count": 66
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28873.0,
"min": 15984.0,
"max": 34830.0,
"count": 66
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7365637813405743,
"min": -1.0000000521540642,
"max": 1.7723414483593731,
"count": 66
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 201.44139863550663,
"min": -30.61880172789097,
"max": 231.10739798098803,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7365637813405743,
"min": -1.0000000521540642,
"max": 1.7723414483593731,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 201.44139863550663,
"min": -30.61880172789097,
"max": 231.10739798098803,
"count": 66
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.017377379075132295,
"min": 0.015793853291808175,
"max": 7.002802916802466,
"count": 66
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.015775972715346,
"min": 1.9410033012827625,
"max": 112.04484666883945,
"count": 66
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679097601",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 Training2 --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": "1679102747"
},
"total": 5145.954889516001,
"count": 1,
"self": 0.5898460180014808,
"children": {
"run_training.setup": {
"total": 0.11495702000001984,
"count": 1,
"self": 0.11495702000001984
},
"TrainerController.start_learning": {
"total": 5145.2500864779995,
"count": 1,
"self": 3.2990414530850103,
"children": {
"TrainerController._reset_env": {
"total": 7.618972613000096,
"count": 1,
"self": 7.618972613000096
},
"TrainerController.advance": {
"total": 5134.233837983916,
"count": 129544,
"self": 3.562600962209217,
"children": {
"env_step": {
"total": 3795.591659764718,
"count": 129544,
"self": 3542.9010099977613,
"children": {
"SubprocessEnvManager._take_step": {
"total": 250.701845610884,
"count": 129544,
"self": 11.026561764104372,
"children": {
"TorchPolicy.evaluate": {
"total": 239.67528384677962,
"count": 125049,
"self": 239.67528384677962
}
}
},
"workers": {
"total": 1.988804156072547,
"count": 129544,
"self": 0.0,
"children": {
"worker_root": {
"total": 5133.177286444883,
"count": 129544,
"is_parallel": true,
"self": 1860.7639490372922,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029119509999873117,
"count": 1,
"is_parallel": true,
"self": 0.0008954109998740023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020165400001133094,
"count": 8,
"is_parallel": true,
"self": 0.0020165400001133094
}
}
},
"UnityEnvironment.step": {
"total": 0.05544391099965651,
"count": 1,
"is_parallel": true,
"self": 0.0005845349992341653,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005388879999372875,
"count": 1,
"is_parallel": true,
"self": 0.0005388879999372875
},
"communicator.exchange": {
"total": 0.05227124200018807,
"count": 1,
"is_parallel": true,
"self": 0.05227124200018807
},
"steps_from_proto": {
"total": 0.0020492460002969892,
"count": 1,
"is_parallel": true,
"self": 0.0004962760008311307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015529699994658586,
"count": 8,
"is_parallel": true,
"self": 0.0015529699994658586
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3272.413337407591,
"count": 129543,
"is_parallel": true,
"self": 68.87378781596817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 52.49474653194375,
"count": 129543,
"is_parallel": true,
"self": 52.49474653194375
},
"communicator.exchange": {
"total": 2936.007783057717,
"count": 129543,
"is_parallel": true,
"self": 2936.007783057717
},
"steps_from_proto": {
"total": 215.037020001962,
"count": 129543,
"is_parallel": true,
"self": 47.79129153915528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 167.2457284628067,
"count": 1036344,
"is_parallel": true,
"self": 167.2457284628067
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1335.0795772569882,
"count": 129544,
"self": 6.1864001906692465,
"children": {
"process_trajectory": {
"total": 272.5216017473181,
"count": 129544,
"self": 272.03023150031777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4913702470003045,
"count": 4,
"self": 0.4913702470003045
}
}
},
"_update_policy": {
"total": 1056.3715753190008,
"count": 923,
"self": 668.5583302909122,
"children": {
"TorchPPOOptimizer.update": {
"total": 387.81324502808866,
"count": 45591,
"self": 387.81324502808866
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.59998942562379e-07,
"count": 1,
"self": 9.59998942562379e-07
},
"TrainerController._save_models": {
"total": 0.09823346799930732,
"count": 1,
"self": 0.0015292120006051846,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09670425599870214,
"count": 1,
"self": 0.09670425599870214
}
}
}
}
}
}
}