ppo-Pyramid / run_logs /timers.json
echrisantus's picture
First Push
864af9a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.21142563223838806,
"min": 0.19861112534999847,
"max": 1.4415829181671143,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 6359.68310546875,
"min": 5983.755859375,
"max": 43731.859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.32358914613723755,
"min": -0.18497344851493835,
"max": 0.3655164837837219,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 83.48600006103516,
"min": -43.838706970214844,
"max": 94.66876983642578,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.1189442127943039,
"min": 0.016770003363490105,
"max": 0.4934137463569641,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 30.687606811523438,
"min": 4.410511016845703,
"max": 116.93905639648438,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06787887551278497,
"min": 0.06435693517172088,
"max": 0.07374799473026762,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9503042571789896,
"min": 0.5124874895427847,
"max": 1.0897169383242726,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012328752583839342,
"min": 0.0007570483189655098,
"max": 0.013134632945279704,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1726025361737508,
"min": 0.009841628146551627,
"max": 0.18388486123391584,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.6126403196285704e-06,
"min": 7.6126403196285704e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010657696447479998,
"min": 0.00010657696447479998,
"max": 0.0033820448726517996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025375142857143,
"min": 0.1025375142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355252,
"min": 1.3886848,
"max": 2.5273481999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002634976771428571,
"min": 0.0002634976771428571,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036889674799999994,
"min": 0.0036889674799999994,
"max": 0.11276208518000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.033586304634809494,
"min": 0.033586304634809494,
"max": 0.5496684908866882,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.4702082872390747,
"min": 0.4702082872390747,
"max": 3.847679376602173,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 509.65,
"min": 460.65625,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30579.0,
"min": 15984.0,
"max": 34849.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1215573396594798,
"min": -1.0000000521540642,
"max": 1.3960843461100012,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 68.41499771922827,
"min": -28.790601529181004,
"max": 89.34939815104008,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1215573396594798,
"min": -1.0000000521540642,
"max": 1.3960843461100012,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 68.41499771922827,
"min": -28.790601529181004,
"max": 89.34939815104008,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.177824501558894,
"min": 0.16023719790246105,
"max": 11.366899609565735,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 10.847294595092535,
"min": 9.51492781424895,
"max": 181.87039375305176,
"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": "1687535816",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 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": "1687539049"
},
"total": 3233.421678868,
"count": 1,
"self": 0.6858759880001344,
"children": {
"run_training.setup": {
"total": 0.055963091999956305,
"count": 1,
"self": 0.055963091999956305
},
"TrainerController.start_learning": {
"total": 3232.6798397879998,
"count": 1,
"self": 2.2838342829772955,
"children": {
"TrainerController._reset_env": {
"total": 1.8172118539999929,
"count": 1,
"self": 1.8172118539999929
},
"TrainerController.advance": {
"total": 3228.3712622740227,
"count": 63571,
"self": 2.3808678770024017,
"children": {
"env_step": {
"total": 2080.7704787829803,
"count": 63571,
"self": 1943.6122782840312,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.73906283399197,
"count": 63571,
"self": 7.290961304988286,
"children": {
"TorchPolicy.evaluate": {
"total": 128.44810152900368,
"count": 62564,
"self": 128.44810152900368
}
}
},
"workers": {
"total": 1.4191376649572476,
"count": 63571,
"self": 0.0,
"children": {
"worker_root": {
"total": 3225.584269900026,
"count": 63571,
"is_parallel": true,
"self": 1456.144509110016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007135500999993383,
"count": 1,
"is_parallel": true,
"self": 0.004885553999997683,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022499469999957,
"count": 8,
"is_parallel": true,
"self": 0.0022499469999957
}
}
},
"UnityEnvironment.step": {
"total": 0.06547702399996069,
"count": 1,
"is_parallel": true,
"self": 0.0006714810001540172,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004013259999737784,
"count": 1,
"is_parallel": true,
"self": 0.0004013259999737784
},
"communicator.exchange": {
"total": 0.0620776029999206,
"count": 1,
"is_parallel": true,
"self": 0.0620776029999206
},
"steps_from_proto": {
"total": 0.002326613999912297,
"count": 1,
"is_parallel": true,
"self": 0.0004989799998611488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018276340000511482,
"count": 8,
"is_parallel": true,
"self": 0.0018276340000511482
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1769.4397607900098,
"count": 63570,
"is_parallel": true,
"self": 47.41367098196747,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.06052751001812,
"count": 63570,
"is_parallel": true,
"self": 26.06052751001812
},
"communicator.exchange": {
"total": 1558.6203793390346,
"count": 63570,
"is_parallel": true,
"self": 1558.6203793390346
},
"steps_from_proto": {
"total": 137.34518295898965,
"count": 63570,
"is_parallel": true,
"self": 29.3280448969532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 108.01713806203645,
"count": 508560,
"is_parallel": true,
"self": 108.01713806203645
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1145.21991561404,
"count": 63571,
"self": 4.479894109077804,
"children": {
"process_trajectory": {
"total": 147.31909175496162,
"count": 63571,
"self": 146.92013946596148,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39895228900013535,
"count": 2,
"self": 0.39895228900013535
}
}
},
"_update_policy": {
"total": 993.4209297500006,
"count": 447,
"self": 425.9990200359965,
"children": {
"TorchPPOOptimizer.update": {
"total": 567.4219097140041,
"count": 22797,
"self": 567.4219097140041
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3429998944047838e-06,
"count": 1,
"self": 1.3429998944047838e-06
},
"TrainerController._save_models": {
"total": 0.20753003399977388,
"count": 1,
"self": 0.00251420299991878,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2050158309998551,
"count": 1,
"self": 0.2050158309998551
}
}
}
}
}
}
}