Brumocas's picture
First Commit
70c96fd verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3484495282173157,
"min": 0.34791043400764465,
"max": 1.4653193950653076,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10341.982421875,
"min": 10341.982421875,
"max": 44451.9296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989954.0,
"min": 29952.0,
"max": 989954.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989954.0,
"min": 29952.0,
"max": 989954.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.586092472076416,
"min": -0.09846219420433044,
"max": 0.6538780331611633,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 163.51980590820312,
"min": -23.63092613220215,
"max": 185.70135498046875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0058241537772119045,
"min": -0.012269620783627033,
"max": 0.2535973787307739,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.62493896484375,
"min": -3.4232242107391357,
"max": 60.102577209472656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06654067325802143,
"min": 0.06349280783001125,
"max": 0.07398776144643003,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9315694256123,
"min": 0.47706710775857847,
"max": 1.1098164216964506,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015651486181533465,
"min": 0.00029251329664254397,
"max": 0.01789314614291595,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2191208065414685,
"min": 0.003217646263067984,
"max": 0.26839719214373925,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.560354622771429e-06,
"min": 7.560354622771429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001058449647188,
"min": 0.0001058449647188,
"max": 0.0033819740726754,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252008571428571,
"min": 0.10252008571428571,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352812,
"min": 1.3886848,
"max": 2.5273246,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002617565628571429,
"min": 0.0002617565628571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003664591880000001,
"min": 0.003664591880000001,
"max": 0.11275972754000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009325594641268253,
"min": 0.009325594641268253,
"max": 0.3769632875919342,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1305583268404007,
"min": 0.1305583268404007,
"max": 2.6387429237365723,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 317.3720930232558,
"min": 296.6666666666667,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27294.0,
"min": 15984.0,
"max": 32114.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6593674260169962,
"min": -1.0000000521540642,
"max": 1.7044999785721302,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 142.70559863746166,
"min": -29.99540165066719,
"max": 170.44999785721302,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6593674260169962,
"min": -1.0000000521540642,
"max": 1.7044999785721302,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 142.70559863746166,
"min": -29.99540165066719,
"max": 170.44999785721302,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.029873822357584748,
"min": 0.028813284123461926,
"max": 7.324588385410607,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5691487227522884,
"min": 2.5691487227522884,
"max": 117.19341416656971,
"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": "1730737042",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730739552"
},
"total": 2510.509903755,
"count": 1,
"self": 0.5873068359996978,
"children": {
"run_training.setup": {
"total": 0.05675380699995003,
"count": 1,
"self": 0.05675380699995003
},
"TrainerController.start_learning": {
"total": 2509.865843112,
"count": 1,
"self": 1.8735984050272236,
"children": {
"TrainerController._reset_env": {
"total": 4.9702354059998015,
"count": 1,
"self": 4.9702354059998015
},
"TrainerController.advance": {
"total": 2502.9218159139737,
"count": 63900,
"self": 1.832807726046667,
"children": {
"env_step": {
"total": 1772.2485650168767,
"count": 63900,
"self": 1593.2588827798731,
"children": {
"SubprocessEnvManager._take_step": {
"total": 177.91244471503728,
"count": 63900,
"self": 5.344891067092021,
"children": {
"TorchPolicy.evaluate": {
"total": 172.56755364794526,
"count": 62562,
"self": 172.56755364794526
}
}
},
"workers": {
"total": 1.0772375219662536,
"count": 63900,
"self": 0.0,
"children": {
"worker_root": {
"total": 2503.7356541240124,
"count": 63900,
"is_parallel": true,
"self": 1050.1220708380922,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019921160001104,
"count": 1,
"is_parallel": true,
"self": 0.0006100160003370547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013820999997733452,
"count": 8,
"is_parallel": true,
"self": 0.0013820999997733452
}
}
},
"UnityEnvironment.step": {
"total": 0.0504119269999137,
"count": 1,
"is_parallel": true,
"self": 0.0006345020001390367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004792580000412272,
"count": 1,
"is_parallel": true,
"self": 0.0004792580000412272
},
"communicator.exchange": {
"total": 0.04738482399989152,
"count": 1,
"is_parallel": true,
"self": 0.04738482399989152
},
"steps_from_proto": {
"total": 0.001913342999841916,
"count": 1,
"is_parallel": true,
"self": 0.0004117449996101641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001501598000231752,
"count": 8,
"is_parallel": true,
"self": 0.001501598000231752
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1453.6135832859202,
"count": 63899,
"is_parallel": true,
"self": 37.787020738929414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.958115279090634,
"count": 63899,
"is_parallel": true,
"self": 25.958115279090634
},
"communicator.exchange": {
"total": 1279.6352093319515,
"count": 63899,
"is_parallel": true,
"self": 1279.6352093319515
},
"steps_from_proto": {
"total": 110.23323793594864,
"count": 63899,
"is_parallel": true,
"self": 23.834160669980974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.39907726596766,
"count": 511192,
"is_parallel": true,
"self": 86.39907726596766
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 728.8404431710503,
"count": 63900,
"self": 3.2374495070630473,
"children": {
"process_trajectory": {
"total": 146.25499137099928,
"count": 63900,
"self": 145.9813129179995,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2736784529997749,
"count": 2,
"self": 0.2736784529997749
}
}
},
"_update_policy": {
"total": 579.348002292988,
"count": 445,
"self": 324.29794234695964,
"children": {
"TorchPPOOptimizer.update": {
"total": 255.05005994602834,
"count": 22845,
"self": 255.05005994602834
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2820000847568735e-06,
"count": 1,
"self": 1.2820000847568735e-06
},
"TrainerController._save_models": {
"total": 0.10019210499922337,
"count": 1,
"self": 0.0015702419996159733,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0986218629996074,
"count": 1,
"self": 0.0986218629996074
}
}
}
}
}
}
}