ppo-PyramidsRND / run_logs /timers.json
Bastian1111's picture
First Push
3fed283
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5209258198738098,
"min": 0.5209258198738098,
"max": 1.4764437675476074,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15694.453125,
"min": 15694.453125,
"max": 44789.3984375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989930.0,
"min": 29928.0,
"max": 989930.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989930.0,
"min": 29928.0,
"max": 989930.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5448301434516907,
"min": -0.11015873402357101,
"max": 0.5937265753746033,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 152.5524444580078,
"min": -26.43809700012207,
"max": 169.2120819091797,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0013570032315328717,
"min": -0.012109323404729366,
"max": 0.2036285400390625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.37996089458465576,
"min": -3.1605334281921387,
"max": 48.870849609375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06981766709248491,
"min": 0.06438662632006326,
"max": 0.07243951589836128,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9774473392947888,
"min": 0.5795161271868903,
"max": 1.0452781784024054,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016989999664864235,
"min": 0.0005274807032160714,
"max": 0.016989999664864235,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23785999530809931,
"min": 0.006329768438592857,
"max": 0.252467917677588,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.3566118335428525e-06,
"min": 7.3566118335428525e-06,
"max": 0.000294759826746725,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010299256566959994,
"min": 0.00010299256566959994,
"max": 0.0035080280306573996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245217142857142,
"min": 0.10245217142857142,
"max": 0.198253275,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343304,
"min": 1.4343304,
"max": 2.5693426,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025497192571428566,
"min": 0.00025497192571428566,
"max": 0.0098255021725,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003569606959999999,
"min": 0.003569606959999999,
"max": 0.11695732573999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0070710256695747375,
"min": 0.00678382208570838,
"max": 0.40224894881248474,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09899435937404633,
"min": 0.09553506970405579,
"max": 3.217991590499878,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 308.6304347826087,
"min": 304.21,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28394.0,
"min": 17494.0,
"max": 32659.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.649402132518189,
"min": -0.9999742455059483,
"max": 1.6757879891991616,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 153.39439832419157,
"min": -31.998401656746864,
"max": 167.57879891991615,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.649402132518189,
"min": -0.9999742455059483,
"max": 1.6757879891991616,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 153.39439832419157,
"min": -31.998401656746864,
"max": 167.57879891991615,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.022763417482623952,
"min": 0.02165965651802253,
"max": 7.518583670258522,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.1169978258840274,
"min": 2.0154592743201647,
"max": 135.3345060646534,
"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": "1691784291",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1691786968"
},
"total": 2677.7718864420003,
"count": 1,
"self": 0.5315962049999143,
"children": {
"run_training.setup": {
"total": 0.045323795999820504,
"count": 1,
"self": 0.045323795999820504
},
"TrainerController.start_learning": {
"total": 2677.1949664410004,
"count": 1,
"self": 1.925647460901473,
"children": {
"TrainerController._reset_env": {
"total": 4.540529111000069,
"count": 1,
"self": 4.540529111000069
},
"TrainerController.advance": {
"total": 2670.6188258130983,
"count": 63799,
"self": 1.9003423540602853,
"children": {
"env_step": {
"total": 1889.5789290620241,
"count": 63799,
"self": 1749.1964439249257,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.25877246702998,
"count": 63799,
"self": 5.930040316043687,
"children": {
"TorchPolicy.evaluate": {
"total": 133.3287321509863,
"count": 62565,
"self": 133.3287321509863
}
}
},
"workers": {
"total": 1.1237126700684712,
"count": 63799,
"self": 0.0,
"children": {
"worker_root": {
"total": 2670.597798126936,
"count": 63799,
"is_parallel": true,
"self": 1065.7395191189194,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022721240000009857,
"count": 1,
"is_parallel": true,
"self": 0.0006230889998732891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016490350001276965,
"count": 8,
"is_parallel": true,
"self": 0.0016490350001276965
}
}
},
"UnityEnvironment.step": {
"total": 0.05769172000009348,
"count": 1,
"is_parallel": true,
"self": 0.0006580980000308045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005694700000731245,
"count": 1,
"is_parallel": true,
"self": 0.0005694700000731245
},
"communicator.exchange": {
"total": 0.05430337999996482,
"count": 1,
"is_parallel": true,
"self": 0.05430337999996482
},
"steps_from_proto": {
"total": 0.0021607720000247355,
"count": 1,
"is_parallel": true,
"self": 0.00042214000018248043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001738631999842255,
"count": 8,
"is_parallel": true,
"self": 0.001738631999842255
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1604.8582790080168,
"count": 63798,
"is_parallel": true,
"self": 41.43543355103475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.993746956977702,
"count": 63798,
"is_parallel": true,
"self": 26.993746956977702
},
"communicator.exchange": {
"total": 1407.0258337789817,
"count": 63798,
"is_parallel": true,
"self": 1407.0258337789817
},
"steps_from_proto": {
"total": 129.40326472102265,
"count": 63798,
"is_parallel": true,
"self": 26.07281598995087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 103.33044873107178,
"count": 510384,
"is_parallel": true,
"self": 103.33044873107178
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 779.1395543970141,
"count": 63799,
"self": 3.4664203521233503,
"children": {
"process_trajectory": {
"total": 129.84699904789,
"count": 63799,
"self": 129.54702901089036,
"children": {
"RLTrainer._checkpoint": {
"total": 0.299970036999639,
"count": 2,
"self": 0.299970036999639
}
}
},
"_update_policy": {
"total": 645.8261349970007,
"count": 454,
"self": 424.5412108660207,
"children": {
"TorchPPOOptimizer.update": {
"total": 221.28492413098002,
"count": 22815,
"self": 221.28492413098002
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0519997886149213e-06,
"count": 1,
"self": 1.0519997886149213e-06
},
"TrainerController._save_models": {
"total": 0.10996300400074688,
"count": 1,
"self": 0.001660386000366998,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10830261800037988,
"count": 1,
"self": 0.10830261800037988
}
}
}
}
}
}
}