testpyramidsrnd / run_logs /timers.json
BekirTaha's picture
First Pyramids
c0bc148
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6424892544746399,
"min": 0.6424892544746399,
"max": 1.4669122695922852,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 19233.55859375,
"min": 19233.55859375,
"max": 44500.25,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479921.0,
"min": 29952.0,
"max": 479921.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479921.0,
"min": 29952.0,
"max": 479921.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.10952070355415344,
"min": -0.11337810009717941,
"max": 0.17591866850852966,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 27.380176544189453,
"min": -27.324121475219727,
"max": 43.627830505371094,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.030589576810598373,
"min": 0.03009730763733387,
"max": 0.2966145873069763,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.647394180297852,
"min": 7.494229793548584,
"max": 71.48411560058594,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06665724948106798,
"min": 0.06665724948106798,
"max": 0.07536791683661549,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9332014927349518,
"min": 0.5275754178563085,
"max": 1.0514537015468723,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.010487714579843061,
"min": 0.00019159560872533104,
"max": 0.010487714579843061,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.14682800411780286,
"min": 0.0017243604785279795,
"max": 0.14682800411780286,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.09343930219e-05,
"min": 2.09343930219e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0002930815023066,
"min": 0.0002930815023066,
"max": 0.0025672583442474,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10697809999999999,
"min": 0.10697809999999999,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4976934,
"min": 1.3773696000000002,
"max": 2.2557526000000006,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00070711219,
"min": 0.00070711219,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.009899570659999999,
"min": 0.009899570659999999,
"max": 0.08562968474,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.026312928646802902,
"min": 0.026312928646802902,
"max": 0.4624808430671692,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.36838099360466003,
"min": 0.36838099360466003,
"max": 3.237365961074829,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 724.5777777777778,
"min": 724.5777777777778,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32606.0,
"min": 15984.0,
"max": 32606.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.47519107427861956,
"min": -1.0000000521540642,
"max": 0.6358157517878633,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 21.38359834253788,
"min": -31.99920167028904,
"max": 24.160998567938805,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.47519107427861956,
"min": -1.0000000521540642,
"max": 0.6358157517878633,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 21.38359834253788,
"min": -31.99920167028904,
"max": 24.160998567938805,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.1987997126325758,
"min": 0.1987997126325758,
"max": 9.305791547521949,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.94598706846591,
"min": 7.678771013743244,
"max": 148.89266476035118,
"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": "1659530113",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1659531123"
},
"total": 1010.0291081169999,
"count": 1,
"self": 0.47682036699984565,
"children": {
"run_training.setup": {
"total": 0.043104706000008264,
"count": 1,
"self": 0.043104706000008264
},
"TrainerController.start_learning": {
"total": 1009.509183044,
"count": 1,
"self": 0.8239632060057147,
"children": {
"TrainerController._reset_env": {
"total": 9.664915161999943,
"count": 1,
"self": 9.664915161999943
},
"TrainerController.advance": {
"total": 998.9219368069946,
"count": 31627,
"self": 0.8772083609968604,
"children": {
"env_step": {
"total": 643.551915622001,
"count": 31627,
"self": 584.7234124049968,
"children": {
"SubprocessEnvManager._take_step": {
"total": 58.40473673298766,
"count": 31627,
"self": 2.551366940016237,
"children": {
"TorchPolicy.evaluate": {
"total": 55.85336979297142,
"count": 31318,
"self": 18.501444193954853,
"children": {
"TorchPolicy.sample_actions": {
"total": 37.35192559901657,
"count": 31318,
"self": 37.35192559901657
}
}
}
}
},
"workers": {
"total": 0.4237664840165962,
"count": 31627,
"self": 0.0,
"children": {
"worker_root": {
"total": 1007.2384630349961,
"count": 31627,
"is_parallel": true,
"self": 476.7345370150002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008617938000043068,
"count": 1,
"is_parallel": true,
"self": 0.004054311999993843,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004563626000049226,
"count": 8,
"is_parallel": true,
"self": 0.004563626000049226
}
}
},
"UnityEnvironment.step": {
"total": 0.04992056700007197,
"count": 1,
"is_parallel": true,
"self": 0.0006310890000804648,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004778899999564601,
"count": 1,
"is_parallel": true,
"self": 0.0004778899999564601
},
"communicator.exchange": {
"total": 0.046993884000016806,
"count": 1,
"is_parallel": true,
"self": 0.046993884000016806
},
"steps_from_proto": {
"total": 0.0018177040000182387,
"count": 1,
"is_parallel": true,
"self": 0.0004541820001122687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00136352199990597,
"count": 8,
"is_parallel": true,
"self": 0.00136352199990597
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 530.5039260199959,
"count": 31626,
"is_parallel": true,
"self": 14.404039232020295,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.919230893969939,
"count": 31626,
"is_parallel": true,
"self": 11.919230893969939
},
"communicator.exchange": {
"total": 456.7268685080145,
"count": 31626,
"is_parallel": true,
"self": 456.7268685080145
},
"steps_from_proto": {
"total": 47.45378738599118,
"count": 31626,
"is_parallel": true,
"self": 12.229282883994983,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.22450450199619,
"count": 253008,
"is_parallel": true,
"self": 35.22450450199619
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 354.4928128239967,
"count": 31627,
"self": 1.4526024430047073,
"children": {
"process_trajectory": {
"total": 80.3340138409909,
"count": 31627,
"self": 80.22803446499086,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10597937600005025,
"count": 1,
"self": 0.10597937600005025
}
}
},
"_update_policy": {
"total": 272.7061965400011,
"count": 206,
"self": 105.87156306000634,
"children": {
"TorchPPOOptimizer.update": {
"total": 166.83463347999475,
"count": 11427,
"self": 166.83463347999475
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1499998890940333e-06,
"count": 1,
"self": 1.1499998890940333e-06
},
"TrainerController._save_models": {
"total": 0.0983667189998414,
"count": 1,
"self": 0.001680786999713746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09668593200012765,
"count": 1,
"self": 0.09668593200012765
}
}
}
}
}
}
}