ppo-Pyramids / run_logs /timers.json
michalcisek5's picture
push first model
c793357
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5462360978126526,
"min": 0.5462360978126526,
"max": 1.4614990949630737,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16430.78125,
"min": 16430.78125,
"max": 44336.03515625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989929.0,
"min": 29873.0,
"max": 989929.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989929.0,
"min": 29873.0,
"max": 989929.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3334370255470276,
"min": -0.08496787399053574,
"max": 0.39903292059898376,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 88.02737426757812,
"min": -20.477256774902344,
"max": 106.14275360107422,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 9.980362892150879,
"min": -0.32218924164772034,
"max": 15.6391019821167,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2634.81591796875,
"min": -79.9029312133789,
"max": 4081.8056640625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06928832805022553,
"min": 0.06509030437053256,
"max": 0.07348976133826433,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9700365927031573,
"min": 0.5717907198345941,
"max": 1.062527542007635,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 8.586760578144874,
"min": 0.0009468831630389371,
"max": 22.023062548112303,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 120.21464809402825,
"min": 0.013256364282545119,
"max": 308.32287567357224,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.605804607621429e-06,
"min": 7.605804607621429e-06,
"max": 0.00029484888921703747,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001064812645067,
"min": 0.0001064812645067,
"max": 0.0036333550888816997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253523571428572,
"min": 0.10253523571428572,
"max": 0.1982829625,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354933,
"min": 1.4354933,
"max": 2.6111183000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002632700478571429,
"min": 0.0002632700478571429,
"max": 0.00982846795375,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036857806700000004,
"min": 0.0036857806700000004,
"max": 0.12113071817,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0064488970674574375,
"min": 0.0064488970674574375,
"max": 0.4282774329185486,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.0902845561504364,
"min": 0.0902845561504364,
"max": 3.4262194633483887,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 475.4193548387097,
"min": 467.258064516129,
"max": 992.40625,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29476.0,
"min": 16416.0,
"max": 33234.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3040825130920561,
"min": -0.9308625513222069,
"max": 1.343324972083792,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 82.15719832479954,
"min": -29.78760164231062,
"max": 85.9727982133627,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3040825130920561,
"min": -0.9308625513222069,
"max": 1.343324972083792,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 82.15719832479954,
"min": -29.78760164231062,
"max": 85.9727982133627,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03159361298908368,
"min": 0.03159361298908368,
"max": 8.899138020241962,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.9903976183122722,
"min": 1.9903976183122722,
"max": 151.28534634411335,
"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": "1678813724",
"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": "1.20.0",
"end_time_seconds": "1678815904"
},
"total": 2180.43221605,
"count": 1,
"self": 0.4929922690002968,
"children": {
"run_training.setup": {
"total": 0.028307444999882136,
"count": 1,
"self": 0.028307444999882136
},
"TrainerController.start_learning": {
"total": 2179.910916336,
"count": 1,
"self": 1.2938566479865585,
"children": {
"TrainerController._reset_env": {
"total": 4.100031967999939,
"count": 1,
"self": 4.100031967999939
},
"TrainerController.advance": {
"total": 2174.435070642013,
"count": 63596,
"self": 1.3668180739418858,
"children": {
"env_step": {
"total": 1439.9003778490428,
"count": 63596,
"self": 1330.8540453960306,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.26137868301271,
"count": 63596,
"self": 4.531391804021723,
"children": {
"TorchPolicy.evaluate": {
"total": 103.72998687899099,
"count": 62565,
"self": 35.57511741796998,
"children": {
"TorchPolicy.sample_actions": {
"total": 68.15486946102101,
"count": 62565,
"self": 68.15486946102101
}
}
}
}
},
"workers": {
"total": 0.7849537699994471,
"count": 63596,
"self": 0.0,
"children": {
"worker_root": {
"total": 2175.0490096539897,
"count": 63596,
"is_parallel": true,
"self": 952.6181933520659,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001717123999924297,
"count": 1,
"is_parallel": true,
"self": 0.0006242259996724897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010928980002518074,
"count": 8,
"is_parallel": true,
"self": 0.0010928980002518074
}
}
},
"UnityEnvironment.step": {
"total": 0.046036350000122184,
"count": 1,
"is_parallel": true,
"self": 0.0005327779999788618,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004623960001026717,
"count": 1,
"is_parallel": true,
"self": 0.0004623960001026717
},
"communicator.exchange": {
"total": 0.043304502999944816,
"count": 1,
"is_parallel": true,
"self": 0.043304502999944816
},
"steps_from_proto": {
"total": 0.0017366730000958341,
"count": 1,
"is_parallel": true,
"self": 0.0004057359999478649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013309370001479692,
"count": 8,
"is_parallel": true,
"self": 0.0013309370001479692
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1222.4308163019239,
"count": 63595,
"is_parallel": true,
"self": 31.801897008036804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.238259682956368,
"count": 63595,
"is_parallel": true,
"self": 22.238259682956368
},
"communicator.exchange": {
"total": 1074.9188694220293,
"count": 63595,
"is_parallel": true,
"self": 1074.9188694220293
},
"steps_from_proto": {
"total": 93.47179018890142,
"count": 63595,
"is_parallel": true,
"self": 22.165148573190663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.30664161571076,
"count": 508760,
"is_parallel": true,
"self": 71.30664161571076
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 733.1678747190288,
"count": 63596,
"self": 2.588271175981845,
"children": {
"process_trajectory": {
"total": 149.72695790804164,
"count": 63596,
"self": 149.5407446150416,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18621329300003708,
"count": 2,
"self": 0.18621329300003708
}
}
},
"_update_policy": {
"total": 580.8526456350053,
"count": 455,
"self": 225.46908313903214,
"children": {
"TorchPPOOptimizer.update": {
"total": 355.38356249597314,
"count": 22785,
"self": 355.38356249597314
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.720000212430023e-07,
"count": 1,
"self": 7.720000212430023e-07
},
"TrainerController._save_models": {
"total": 0.0819563059999382,
"count": 1,
"self": 0.001289180000185297,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0806671259997529,
"count": 1,
"self": 0.0806671259997529
}
}
}
}
}
}
}