ppo-PyramidsRND / run_logs /timers.json
claterza's picture
First commit of ppo-PyramidsRND
1d5bb68
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5796468257904053,
"min": 0.5776888132095337,
"max": 1.4805067777633667,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17472.873046875,
"min": 17358.392578125,
"max": 44912.65234375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989999.0,
"min": 29952.0,
"max": 989999.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989999.0,
"min": 29952.0,
"max": 989999.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3169468641281128,
"min": -0.11680218577384949,
"max": 0.3169468641281128,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 83.04007720947266,
"min": -28.266128540039062,
"max": 83.04007720947266,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.008593330159783363,
"min": -0.014173561707139015,
"max": 0.2885436415672302,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.2514524459838867,
"min": -3.486696243286133,
"max": 69.25047302246094,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07040219646566578,
"min": 0.06528724816647859,
"max": 0.07415676041852216,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0560329469849867,
"min": 0.4944393681623202,
"max": 1.0560329469849867,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013976128632511855,
"min": 0.00047259594567965917,
"max": 0.014166723930386416,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20964192948767782,
"min": 0.006143747293835569,
"max": 0.20964192948767782,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.527397490899999e-06,
"min": 7.527397490899999e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011291096236349998,
"min": 0.00011291096236349998,
"max": 0.0032562509145831,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025091,
"min": 0.1025091,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376365,
"min": 1.3691136000000002,
"max": 2.3854169,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026065909,
"min": 0.00026065909,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00390988635,
"min": 0.00390988635,
"max": 0.10856314831000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012977433390915394,
"min": 0.012977433390915394,
"max": 0.43007662892341614,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19466149806976318,
"min": 0.1819048821926117,
"max": 3.0105364322662354,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 494.6271186440678,
"min": 494.6271186440678,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29183.0,
"min": 15984.0,
"max": 33571.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2341016650957577,
"min": -1.0000000521540642,
"max": 1.2831812312360853,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 72.8119982406497,
"min": -32.000001668930054,
"max": 82.12359879910946,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2341016650957577,
"min": -1.0000000521540642,
"max": 1.2831812312360853,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 72.8119982406497,
"min": -32.000001668930054,
"max": 82.12359879910946,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0670958287871869,
"min": 0.0670958287871869,
"max": 8.421874239109457,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.9586538984440267,
"min": 3.9586538984440267,
"max": 134.7499878257513,
"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": "1674100052",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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 Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674102295"
},
"total": 2243.3575468699996,
"count": 1,
"self": 0.44156413900009284,
"children": {
"run_training.setup": {
"total": 0.11697659599997223,
"count": 1,
"self": 0.11697659599997223
},
"TrainerController.start_learning": {
"total": 2242.7990061349997,
"count": 1,
"self": 1.5679157619861144,
"children": {
"TrainerController._reset_env": {
"total": 10.679894170000011,
"count": 1,
"self": 10.679894170000011
},
"TrainerController.advance": {
"total": 2230.4620356350138,
"count": 63421,
"self": 1.6665844139706678,
"children": {
"env_step": {
"total": 1532.9269513530112,
"count": 63421,
"self": 1408.2036648770172,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.7561339909987,
"count": 63421,
"self": 4.988088462967198,
"children": {
"TorchPolicy.evaluate": {
"total": 118.76804552803151,
"count": 62563,
"self": 39.58451526699588,
"children": {
"TorchPolicy.sample_actions": {
"total": 79.18353026103563,
"count": 62563,
"self": 79.18353026103563
}
}
}
}
},
"workers": {
"total": 0.9671524849953244,
"count": 63421,
"self": 0.0,
"children": {
"worker_root": {
"total": 2237.495885190973,
"count": 63421,
"is_parallel": true,
"self": 946.3047359679686,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005418995999946219,
"count": 1,
"is_parallel": true,
"self": 0.0032116189998987466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022073770000474724,
"count": 8,
"is_parallel": true,
"self": 0.0022073770000474724
}
}
},
"UnityEnvironment.step": {
"total": 0.05148142899997765,
"count": 1,
"is_parallel": true,
"self": 0.000516736999998102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004913120000082927,
"count": 1,
"is_parallel": true,
"self": 0.0004913120000082927
},
"communicator.exchange": {
"total": 0.04871858999996448,
"count": 1,
"is_parallel": true,
"self": 0.04871858999996448
},
"steps_from_proto": {
"total": 0.0017547900000067784,
"count": 1,
"is_parallel": true,
"self": 0.00047309099994663484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012816990000601436,
"count": 8,
"is_parallel": true,
"self": 0.0012816990000601436
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1291.1911492230042,
"count": 63420,
"is_parallel": true,
"self": 31.031749090042922,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.50559577099358,
"count": 63420,
"is_parallel": true,
"self": 25.50559577099358
},
"communicator.exchange": {
"total": 1128.2101073439983,
"count": 63420,
"is_parallel": true,
"self": 1128.2101073439983
},
"steps_from_proto": {
"total": 106.4436970179695,
"count": 63420,
"is_parallel": true,
"self": 26.274784624006998,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.1689123939625,
"count": 507360,
"is_parallel": true,
"self": 80.1689123939625
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 695.8684998680319,
"count": 63421,
"self": 2.7910029020392813,
"children": {
"process_trajectory": {
"total": 157.79834694999226,
"count": 63421,
"self": 157.58141982699271,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2169271229995502,
"count": 2,
"self": 0.2169271229995502
}
}
},
"_update_policy": {
"total": 535.2791500160004,
"count": 441,
"self": 206.59106406301112,
"children": {
"TorchPPOOptimizer.update": {
"total": 328.68808595298924,
"count": 22767,
"self": 328.68808595298924
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.589998626324814e-07,
"count": 1,
"self": 9.589998626324814e-07
},
"TrainerController._save_models": {
"total": 0.08915960900003483,
"count": 1,
"self": 0.0015788949999659962,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08758071400006884,
"count": 1,
"self": 0.08758071400006884
}
}
}
}
}
}
}