nossal's picture
limited training
2c4a130
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7093910574913025,
"min": 0.6764631271362305,
"max": 1.373907446861267,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 21270.380859375,
"min": 20337.1875,
"max": 41678.85546875,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479995.0,
"min": 29952.0,
"max": 479995.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479995.0,
"min": 29952.0,
"max": 479995.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.04448532313108444,
"min": -0.23997020721435547,
"max": -0.027672898024320602,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -10.80993366241455,
"min": -56.87294006347656,
"max": -6.696841239929199,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0288513395935297,
"min": 0.027196792885661125,
"max": 0.3839012086391449,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.010875701904297,
"min": 6.5816240310668945,
"max": 90.98458862304688,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0615943463202742,
"min": 0.0615943463202742,
"max": 0.07218162642943309,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.8623208484838387,
"min": 0.5035907415955477,
"max": 1.0353437023894752,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.003753676876851937,
"min": 0.00015394218589245425,
"max": 0.007644571844832085,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.05255147627592712,
"min": 0.002001248416601905,
"max": 0.053512002913824595,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.1055421552985713e-05,
"min": 2.1055421552985713e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0002947759017418,
"min": 0.0002947759017418,
"max": 0.0030845072718309998,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10701844285714286,
"min": 0.10701844285714286,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4982582,
"min": 1.3773696000000002,
"max": 2.4214952000000003,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007111424414285716,
"min": 0.0007111424414285716,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.009955994180000004,
"min": 0.009955994180000004,
"max": 0.10284408310000001,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.02558114007115364,
"min": 0.02558114007115364,
"max": 0.47173407673835754,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.35813596844673157,
"min": 0.35813596844673157,
"max": 3.302138566970825,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 910.5757575757576,
"min": 910.5757575757576,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30049.0,
"min": 15984.0,
"max": 33096.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.365618224171075,
"min": -1.0000000521540642,
"max": -0.365618224171075,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -12.065401397645473,
"min": -30.47680163383484,
"max": -12.065401397645473,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.365618224171075,
"min": -1.0000000521540642,
"max": -0.365618224171075,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -12.065401397645473,
"min": -30.47680163383484,
"max": -12.065401397645473,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.24484323879534547,
"min": 0.24484323879534547,
"max": 9.187775854952633,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.0798268802464,
"min": 7.888044430874288,
"max": 147.00441367924213,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677790008",
"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 Training1 --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": "1.22.4",
"end_time_seconds": "1677791126"
},
"total": 1117.8002106349998,
"count": 1,
"self": 0.4748282449997987,
"children": {
"run_training.setup": {
"total": 0.11627255700000205,
"count": 1,
"self": 0.11627255700000205
},
"TrainerController.start_learning": {
"total": 1117.209109833,
"count": 1,
"self": 0.8046991540450108,
"children": {
"TrainerController._reset_env": {
"total": 6.508378255000025,
"count": 1,
"self": 6.508378255000025
},
"TrainerController.advance": {
"total": 1109.8069332769549,
"count": 31604,
"self": 0.8244418889946701,
"children": {
"env_step": {
"total": 729.523099239977,
"count": 31604,
"self": 665.9558106409074,
"children": {
"SubprocessEnvManager._take_step": {
"total": 63.076812919016675,
"count": 31604,
"self": 2.5039575190166943,
"children": {
"TorchPolicy.evaluate": {
"total": 60.57285539999998,
"count": 31303,
"self": 20.514133529984292,
"children": {
"TorchPolicy.sample_actions": {
"total": 40.05872187001569,
"count": 31303,
"self": 40.05872187001569
}
}
}
}
},
"workers": {
"total": 0.49047568005289577,
"count": 31604,
"self": 0.0,
"children": {
"worker_root": {
"total": 1114.5009795189649,
"count": 31604,
"is_parallel": true,
"self": 512.5158561439875,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019651810000596015,
"count": 1,
"is_parallel": true,
"self": 0.0007043890002478292,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012607919998117723,
"count": 8,
"is_parallel": true,
"self": 0.0012607919998117723
}
}
},
"UnityEnvironment.step": {
"total": 0.05218136900020909,
"count": 1,
"is_parallel": true,
"self": 0.0005571350002355757,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004354970001259062,
"count": 1,
"is_parallel": true,
"self": 0.0004354970001259062
},
"communicator.exchange": {
"total": 0.04931732499994723,
"count": 1,
"is_parallel": true,
"self": 0.04931732499994723
},
"steps_from_proto": {
"total": 0.0018714119999003742,
"count": 1,
"is_parallel": true,
"self": 0.00045272600004864216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001418685999851732,
"count": 8,
"is_parallel": true,
"self": 0.001418685999851732
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 601.9851233749773,
"count": 31603,
"is_parallel": true,
"self": 16.497958011965466,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.996678366991318,
"count": 31603,
"is_parallel": true,
"self": 11.996678366991318
},
"communicator.exchange": {
"total": 524.9487063110244,
"count": 31603,
"is_parallel": true,
"self": 524.9487063110244
},
"steps_from_proto": {
"total": 48.54178068499618,
"count": 31603,
"is_parallel": true,
"self": 11.846110219954426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.69567046504176,
"count": 252824,
"is_parallel": true,
"self": 36.69567046504176
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 379.4593921479832,
"count": 31604,
"self": 1.370049027980258,
"children": {
"process_trajectory": {
"total": 84.0740382570034,
"count": 31604,
"self": 83.9787177500034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09532050699999672,
"count": 1,
"self": 0.09532050699999672
}
}
},
"_update_policy": {
"total": 294.0153048629995,
"count": 219,
"self": 113.56728521196737,
"children": {
"TorchPPOOptimizer.update": {
"total": 180.44801965103215,
"count": 11355,
"self": 180.44801965103215
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.760002856433857e-07,
"count": 1,
"self": 8.760002856433857e-07
},
"TrainerController._save_models": {
"total": 0.08909827099978429,
"count": 1,
"self": 0.0013929500000813277,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08770532099970296,
"count": 1,
"self": 0.08770532099970296
}
}
}
}
}
}
}