ppo-pyramid / run_logs /timers.json
MRNH's picture
First Push
345c02f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.28938373923301697,
"min": 0.28869688510894775,
"max": 1.4830058813095093,
"count": 62
},
"Pyramids.Policy.Entropy.sum": {
"value": 8686.142578125,
"min": 8686.142578125,
"max": 44988.46484375,
"count": 62
},
"Pyramids.Step.mean": {
"value": 1859970.0,
"min": 29952.0,
"max": 1859970.0,
"count": 62
},
"Pyramids.Step.sum": {
"value": 1859970.0,
"min": 29952.0,
"max": 1859970.0,
"count": 62
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6734209060668945,
"min": -0.09665857255458832,
"max": 0.6920368671417236,
"count": 62
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 188.55784606933594,
"min": -23.391374588012695,
"max": 199.9986572265625,
"count": 62
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0006567835225723684,
"min": -0.05253283679485321,
"max": 0.23250968754291534,
"count": 62
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.183899387717247,
"min": -14.026267051696777,
"max": 55.80232620239258,
"count": 62
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06742039654840563,
"min": 0.06500617718123193,
"max": 0.07376132471219686,
"count": 62
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9438855516776788,
"min": 0.4760923674065839,
"max": 1.0854322901121158,
"count": 62
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013997409617950938,
"min": 0.0005148802321640378,
"max": 0.016071638004394203,
"count": 62
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19596373465131312,
"min": 0.006693443018132491,
"max": 0.22500293206151886,
"count": 62
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00011545030437372857,
"min": 0.00011545030437372857,
"max": 0.00029838354339596195,
"count": 62
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0016163042612322,
"min": 0.0016163042612322,
"max": 0.003969038576987166,
"count": 62
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.13848341428571428,
"min": 0.13848341428571428,
"max": 0.19946118095238097,
"count": 62
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.9387678,
"min": 1.3897045333333333,
"max": 2.812505933333333,
"count": 62
},
"Pyramids.Policy.Beta.mean": {
"value": 0.003854493087142858,
"min": 0.003854493087142858,
"max": 0.009946171977142856,
"count": 62
},
"Pyramids.Policy.Beta.sum": {
"value": 0.05396290322000001,
"min": 0.05396290322000001,
"max": 0.13230898205,
"count": 62
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005462401080876589,
"min": 0.0045905704610049725,
"max": 0.3844895362854004,
"count": 62
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07647361606359482,
"min": 0.06426798552274704,
"max": 2.6914267539978027,
"count": 62
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 305.68,
"min": 284.5,
"max": 999.0,
"count": 62
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30568.0,
"min": 15984.0,
"max": 32736.0,
"count": 62
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5942999821901322,
"min": -1.0000000521540642,
"max": 1.6566607655555594,
"count": 62
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 159.4299982190132,
"min": -32.000001668930054,
"max": 168.97939808666706,
"count": 62
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5942999821901322,
"min": -1.0000000521540642,
"max": 1.6566607655555594,
"count": 62
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 159.4299982190132,
"min": -32.000001668930054,
"max": 168.97939808666706,
"count": 62
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.017400569220480975,
"min": 0.01684341960193991,
"max": 8.022843619808555,
"count": 62
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.7400569220480975,
"min": 1.4181207066139905,
"max": 128.36549791693687,
"count": 62
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 62
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 62
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691756474",
"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": "1691760959"
},
"total": 4484.808707615,
"count": 1,
"self": 0.3248037059993294,
"children": {
"run_training.setup": {
"total": 0.04586917300002824,
"count": 1,
"self": 0.04586917300002824
},
"TrainerController.start_learning": {
"total": 4484.438034736,
"count": 1,
"self": 2.9494383159872086,
"children": {
"TrainerController._reset_env": {
"total": 4.271625298999993,
"count": 1,
"self": 4.271625298999993
},
"TrainerController.advance": {
"total": 4477.060918841013,
"count": 119613,
"self": 2.9711518300036914,
"children": {
"env_step": {
"total": 3215.557095362953,
"count": 119613,
"self": 2987.5792016269093,
"children": {
"SubprocessEnvManager._take_step": {
"total": 226.11080068908996,
"count": 119613,
"self": 9.734088596051151,
"children": {
"TorchPolicy.evaluate": {
"total": 216.3767120930388,
"count": 117049,
"self": 216.3767120930388
}
}
},
"workers": {
"total": 1.8670930469537552,
"count": 119612,
"self": 0.0,
"children": {
"worker_root": {
"total": 4473.663049050969,
"count": 119612,
"is_parallel": true,
"self": 1727.468788368034,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005082392000076652,
"count": 1,
"is_parallel": true,
"self": 0.0035086830001773706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015737089998992815,
"count": 8,
"is_parallel": true,
"self": 0.0015737089998992815
}
}
},
"UnityEnvironment.step": {
"total": 0.05523085600009381,
"count": 1,
"is_parallel": true,
"self": 0.0006126190000941278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004729639999823121,
"count": 1,
"is_parallel": true,
"self": 0.0004729639999823121
},
"communicator.exchange": {
"total": 0.05211275299996032,
"count": 1,
"is_parallel": true,
"self": 0.05211275299996032
},
"steps_from_proto": {
"total": 0.0020325200000570476,
"count": 1,
"is_parallel": true,
"self": 0.00045965000003889145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015728700000181561,
"count": 8,
"is_parallel": true,
"self": 0.0015728700000181561
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2746.194260682935,
"count": 119611,
"is_parallel": true,
"self": 67.8919517017398,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 46.479384981117505,
"count": 119611,
"is_parallel": true,
"self": 46.479384981117505
},
"communicator.exchange": {
"total": 2414.2851384260775,
"count": 119611,
"is_parallel": true,
"self": 2414.2851384260775
},
"steps_from_proto": {
"total": 217.5377855739996,
"count": 119611,
"is_parallel": true,
"self": 44.18876127991132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 173.34902429408828,
"count": 956888,
"is_parallel": true,
"self": 173.34902429408828
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1258.5326716480556,
"count": 119612,
"self": 5.538928714040367,
"children": {
"process_trajectory": {
"total": 227.9387620760192,
"count": 119612,
"self": 227.54747672401913,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3912853520000681,
"count": 3,
"self": 0.3912853520000681
}
}
},
"_update_policy": {
"total": 1025.054980857996,
"count": 855,
"self": 668.8552328499748,
"children": {
"TorchPPOOptimizer.update": {
"total": 356.1997480080213,
"count": 42675,
"self": 356.1997480080213
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1849997463286854e-06,
"count": 1,
"self": 1.1849997463286854e-06
},
"TrainerController._save_models": {
"total": 0.15605109500029357,
"count": 1,
"self": 0.002077164000183984,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1539739310001096,
"count": 1,
"self": 0.1539739310001096
}
}
}
}
}
}
}