ppo-PyramidsRND / run_logs /timers.json
pabloyesteb's picture
Subida I
98eb99a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.32608816027641296,
"min": 0.3260343372821808,
"max": 1.4834710359573364,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9860.90625,
"min": 9629.75,
"max": 45002.578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989958.0,
"min": 29952.0,
"max": 989958.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989958.0,
"min": 29952.0,
"max": 989958.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4889722764492035,
"min": -0.0827411636710167,
"max": 0.5884976387023926,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 133.00045776367188,
"min": -19.94062042236328,
"max": 160.07135009765625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.018497852608561516,
"min": -0.018497852608561516,
"max": 0.26822128891944885,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -5.031415939331055,
"min": -5.031415939331055,
"max": 64.37310791015625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06846923154430837,
"min": 0.06331308550439078,
"max": 0.0734606170154934,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9585692416203172,
"min": 0.4967418422241061,
"max": 1.0548762422857931,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01632231401597265,
"min": 0.0006867401268466135,
"max": 0.017558857621283484,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22851239622361713,
"min": 0.007554141395312749,
"max": 0.24582400669796875,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.700476004635716e-06,
"min": 7.700476004635716e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010780666406490002,
"min": 0.00010780666406490002,
"max": 0.003256397314534299,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256679285714286,
"min": 0.10256679285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359351,
"min": 1.3691136000000002,
"max": 2.4840998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002664226064285716,
"min": 0.0002664226064285716,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037299164900000017,
"min": 0.0037299164900000017,
"max": 0.10856802343,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010939222760498524,
"min": 0.010939222760498524,
"max": 0.30432891845703125,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15314911305904388,
"min": 0.15314911305904388,
"max": 2.1303024291992188,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 365.175,
"min": 328.57471264367814,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29214.0,
"min": 15984.0,
"max": 32773.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5848124746233225,
"min": -1.0000000521540642,
"max": 1.6680941045284272,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 126.7849979698658,
"min": -32.000001668930054,
"max": 142.0559982061386,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5848124746233225,
"min": -1.0000000521540642,
"max": 1.6680941045284272,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 126.7849979698658,
"min": -32.000001668930054,
"max": 142.0559982061386,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04148480015937821,
"min": 0.040637715126858785,
"max": 5.9434097283519804,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.318784012750257,
"min": 3.318784012750257,
"max": 95.09455565363169,
"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": "1692487452",
"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": "1692489868"
},
"total": 2415.498542838,
"count": 1,
"self": 0.495236699000543,
"children": {
"run_training.setup": {
"total": 0.07260470699998223,
"count": 1,
"self": 0.07260470699998223
},
"TrainerController.start_learning": {
"total": 2414.9307014319998,
"count": 1,
"self": 1.4973012879968337,
"children": {
"TrainerController._reset_env": {
"total": 4.916503325000008,
"count": 1,
"self": 4.916503325000008
},
"TrainerController.advance": {
"total": 2408.4185666210033,
"count": 63863,
"self": 1.5154665369973372,
"children": {
"env_step": {
"total": 1701.9834163420128,
"count": 63863,
"self": 1583.2717276829908,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.76041172798875,
"count": 63863,
"self": 4.990111474026207,
"children": {
"TorchPolicy.evaluate": {
"total": 112.77030025396255,
"count": 62566,
"self": 112.77030025396255
}
}
},
"workers": {
"total": 0.9512769310332487,
"count": 63863,
"self": 0.0,
"children": {
"worker_root": {
"total": 2409.2957030169414,
"count": 63863,
"is_parallel": true,
"self": 950.3409683858717,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006422931000088283,
"count": 1,
"is_parallel": true,
"self": 0.004851466000332039,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015714649997562447,
"count": 8,
"is_parallel": true,
"self": 0.0015714649997562447
}
}
},
"UnityEnvironment.step": {
"total": 0.04976937899994027,
"count": 1,
"is_parallel": true,
"self": 0.0006456529999923077,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005717809999623569,
"count": 1,
"is_parallel": true,
"self": 0.0005717809999623569
},
"communicator.exchange": {
"total": 0.04651998499991805,
"count": 1,
"is_parallel": true,
"self": 0.04651998499991805
},
"steps_from_proto": {
"total": 0.0020319600000675564,
"count": 1,
"is_parallel": true,
"self": 0.00039121600002545165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016407440000421047,
"count": 8,
"is_parallel": true,
"self": 0.0016407440000421047
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1458.9547346310696,
"count": 63862,
"is_parallel": true,
"self": 36.96907865810954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.42175522797504,
"count": 63862,
"is_parallel": true,
"self": 24.42175522797504
},
"communicator.exchange": {
"total": 1283.5673147770228,
"count": 63862,
"is_parallel": true,
"self": 1283.5673147770228
},
"steps_from_proto": {
"total": 113.99658596796235,
"count": 63862,
"is_parallel": true,
"self": 22.70101223880124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 91.2955737291611,
"count": 510896,
"is_parallel": true,
"self": 91.2955737291611
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 704.9196837419933,
"count": 63863,
"self": 2.9158751109690684,
"children": {
"process_trajectory": {
"total": 117.81247502202996,
"count": 63863,
"self": 117.58268309902951,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22979192300044815,
"count": 2,
"self": 0.22979192300044815
}
}
},
"_update_policy": {
"total": 584.1913336089942,
"count": 443,
"self": 383.9529126359703,
"children": {
"TorchPPOOptimizer.update": {
"total": 200.23842097302395,
"count": 22812,
"self": 200.23842097302395
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1539996194187552e-06,
"count": 1,
"self": 1.1539996194187552e-06
},
"TrainerController._save_models": {
"total": 0.09832904399991094,
"count": 1,
"self": 0.0014845659998172778,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09684447800009366,
"count": 1,
"self": 0.09684447800009366
}
}
}
}
}
}
}