PPO-PyramidsRND / run_logs /timers.json
AlGM93's picture
Baseline Training.
7b2fe4c verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.19822649657726288,
"min": 0.19822649657726288,
"max": 1.3145568370819092,
"count": 75
},
"Pyramids.Policy.Entropy.sum": {
"value": 5984.8544921875,
"min": 5984.8544921875,
"max": 39878.39453125,
"count": 75
},
"Pyramids.Step.mean": {
"value": 2249994.0,
"min": 29952.0,
"max": 2249994.0,
"count": 75
},
"Pyramids.Step.sum": {
"value": 2249994.0,
"min": 29952.0,
"max": 2249994.0,
"count": 75
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8674768805503845,
"min": -0.1273331642150879,
"max": 0.881772518157959,
"count": 75
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 258.50811767578125,
"min": -30.687292098999023,
"max": 270.70416259765625,
"count": 75
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010573622770607471,
"min": -0.007379718590527773,
"max": 0.5427152514457703,
"count": 75
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.150939464569092,
"min": -2.14749813079834,
"max": 128.62351989746094,
"count": 75
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0674975711611166,
"min": 0.06465808856559711,
"max": 0.07341328798922606,
"count": 75
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9449659962556324,
"min": 0.507544210740638,
"max": 1.101199319838391,
"count": 75
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013348374341148883,
"min": 0.0005144041414155122,
"max": 0.01720798250226792,
"count": 75
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18687724077608436,
"min": 0.00720165797981717,
"max": 0.24091175503175086,
"count": 75
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.644089594829761e-05,
"min": 7.644089594829761e-05,
"max": 0.00029838354339596195,
"count": 75
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0010701725432761666,
"min": 0.0010701725432761666,
"max": 0.0039692394769202,
"count": 75
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12548027380952384,
"min": 0.12548027380952384,
"max": 0.19946118095238097,
"count": 75
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.7567238333333337,
"min": 1.3962282666666668,
"max": 2.7230798000000003,
"count": 75
},
"Pyramids.Policy.Beta.mean": {
"value": 0.002555479353571429,
"min": 0.002555479353571429,
"max": 0.009946171977142856,
"count": 75
},
"Pyramids.Policy.Beta.sum": {
"value": 0.035776710950000006,
"min": 0.035776710950000006,
"max": 0.13231567202000002,
"count": 75
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006926466710865498,
"min": 0.006886098999530077,
"max": 0.530479371547699,
"count": 75
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09697053581476212,
"min": 0.09640538692474365,
"max": 3.713355541229248,
"count": 75
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 224.97142857142856,
"min": 204.19117647058823,
"max": 999.0,
"count": 75
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31496.0,
"min": 15984.0,
"max": 32687.0,
"count": 75
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.746448559846197,
"min": -1.0000000521540642,
"max": 1.7962335610259188,
"count": 75
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 244.50279837846756,
"min": -29.99400170892477,
"max": 248.94299843907356,
"count": 75
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.746448559846197,
"min": -1.0000000521540642,
"max": 1.7962335610259188,
"count": 75
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 244.50279837846756,
"min": -29.99400170892477,
"max": 248.94299843907356,
"count": 75
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01627369362961742,
"min": 0.015415373671870668,
"max": 11.634085934609175,
"count": 75
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.278317108146439,
"min": 2.1163563930167584,
"max": 186.1453749537468,
"count": 75
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 75
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 75
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709031137",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709036678"
},
"total": 5541.519392178,
"count": 1,
"self": 0.3293523180009288,
"children": {
"run_training.setup": {
"total": 0.06004563299984511,
"count": 1,
"self": 0.06004563299984511
},
"TrainerController.start_learning": {
"total": 5541.129994227,
"count": 1,
"self": 3.3019927479344915,
"children": {
"TrainerController._reset_env": {
"total": 2.3698369749999983,
"count": 1,
"self": 2.3698369749999983
},
"TrainerController.advance": {
"total": 5535.302181681065,
"count": 147017,
"self": 3.4022202761552762,
"children": {
"env_step": {
"total": 4075.9017116920086,
"count": 147017,
"self": 3763.2208048166444,
"children": {
"SubprocessEnvManager._take_step": {
"total": 310.67336076921333,
"count": 147017,
"self": 11.67177290528548,
"children": {
"TorchPolicy.evaluate": {
"total": 299.00158786392785,
"count": 141783,
"self": 299.00158786392785
}
}
},
"workers": {
"total": 2.007546106150812,
"count": 147016,
"self": 0.0,
"children": {
"worker_root": {
"total": 5529.409981234124,
"count": 147016,
"is_parallel": true,
"self": 2046.0570791030977,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022266630001013255,
"count": 1,
"is_parallel": true,
"self": 0.0007257089998802257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015009540002210997,
"count": 8,
"is_parallel": true,
"self": 0.0015009540002210997
}
}
},
"UnityEnvironment.step": {
"total": 0.053223979999984294,
"count": 1,
"is_parallel": true,
"self": 0.000646041999971203,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005833440000060364,
"count": 1,
"is_parallel": true,
"self": 0.0005833440000060364
},
"communicator.exchange": {
"total": 0.05016847499996402,
"count": 1,
"is_parallel": true,
"self": 0.05016847499996402
},
"steps_from_proto": {
"total": 0.001826119000043036,
"count": 1,
"is_parallel": true,
"self": 0.00038147900022522663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014446399998178094,
"count": 8,
"is_parallel": true,
"self": 0.0014446399998178094
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3483.352902131026,
"count": 147015,
"is_parallel": true,
"self": 83.07588477287209,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 60.2820978520333,
"count": 147015,
"is_parallel": true,
"self": 60.2820978520333
},
"communicator.exchange": {
"total": 3094.217723935998,
"count": 147015,
"is_parallel": true,
"self": 3094.217723935998
},
"steps_from_proto": {
"total": 245.77719557012279,
"count": 147015,
"is_parallel": true,
"self": 49.82663293639416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 195.95056263372862,
"count": 1176120,
"is_parallel": true,
"self": 195.95056263372862
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1455.9982497129015,
"count": 147016,
"self": 6.681504029865891,
"children": {
"process_trajectory": {
"total": 303.20746517303746,
"count": 147016,
"self": 302.79777052303757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40969464999989214,
"count": 4,
"self": 0.40969464999989214
}
}
},
"_update_policy": {
"total": 1146.1092805099981,
"count": 1050,
"self": 673.6821299611017,
"children": {
"TorchPPOOptimizer.update": {
"total": 472.4271505488964,
"count": 51693,
"self": 472.4271505488964
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4600000213249587e-06,
"count": 1,
"self": 1.4600000213249587e-06
},
"TrainerController._save_models": {
"total": 0.1559813630001372,
"count": 1,
"self": 0.0020713379999506287,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15391002500018658,
"count": 1,
"self": 0.15391002500018658
}
}
}
}
}
}
}