ppo-PyramidsRND / run_logs /timers.json
PR0G3T's picture
First Push
21931e8 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4297022819519043,
"min": 0.4297022819519043,
"max": 1.4238770008087158,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12856.6923828125,
"min": 12856.6923828125,
"max": 43194.734375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989966.0,
"min": 29952.0,
"max": 989966.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989966.0,
"min": 29952.0,
"max": 989966.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4224453568458557,
"min": -0.08846589922904968,
"max": 0.49303996562957764,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 111.52557373046875,
"min": -21.231815338134766,
"max": 134.59991455078125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014988711103796959,
"min": -0.020409002900123596,
"max": 0.48107588291168213,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.957019805908203,
"min": -5.408385753631592,
"max": 114.01498413085938,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07013877678178997,
"min": 0.06522971540904283,
"max": 0.07411378908583278,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0520816517268494,
"min": 0.4877279788756143,
"max": 1.0520816517268494,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014443471577354048,
"min": 0.00026592585654052717,
"max": 0.01705318162471192,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21665207366031072,
"min": 0.003191110278486326,
"max": 0.2387445427459669,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.441337519586666e-06,
"min": 7.441337519586666e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011162006279379999,
"min": 0.00011162006279379999,
"max": 0.0035090246303251995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248041333333334,
"min": 0.10248041333333334,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372062000000002,
"min": 1.3886848,
"max": 2.5696748,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257793292,
"min": 0.000257793292,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038668993800000002,
"min": 0.0038668993800000002,
"max": 0.11699051252,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013424879871308804,
"min": 0.013424879871308804,
"max": 0.5771549940109253,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20137320458889008,
"min": 0.19798414409160614,
"max": 4.0400848388671875,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 454.796875,
"min": 371.02564102564105,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29107.0,
"min": 15984.0,
"max": 32662.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.382165054598498,
"min": -1.0000000521540642,
"max": 1.5530547720112213,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 87.07639843970537,
"min": -31.99640166759491,
"max": 120.5763985067606,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.382165054598498,
"min": -1.0000000521540642,
"max": 1.5530547720112213,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 87.07639843970537,
"min": -31.99640166759491,
"max": 120.5763985067606,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06308401121546807,
"min": 0.0571971727177909,
"max": 11.60928548220545,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.974292706574488,
"min": 3.974292706574488,
"max": 185.7485677152872,
"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": "1746005744",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746008982"
},
"total": 3237.6789368279997,
"count": 1,
"self": 0.6307684929997777,
"children": {
"run_training.setup": {
"total": 0.030044804999988628,
"count": 1,
"self": 0.030044804999988628
},
"TrainerController.start_learning": {
"total": 3237.0181235299997,
"count": 1,
"self": 2.385602878962345,
"children": {
"TrainerController._reset_env": {
"total": 3.134230149000132,
"count": 1,
"self": 3.134230149000132
},
"TrainerController.advance": {
"total": 3231.419323212037,
"count": 63718,
"self": 2.5196143550210763,
"children": {
"env_step": {
"total": 2153.7292056399956,
"count": 63718,
"self": 1984.223576123958,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.2022035299956,
"count": 63718,
"self": 7.198287286938921,
"children": {
"TorchPolicy.evaluate": {
"total": 161.00391624305666,
"count": 62558,
"self": 161.00391624305666
}
}
},
"workers": {
"total": 1.3034259860419297,
"count": 63718,
"self": 0.0,
"children": {
"worker_root": {
"total": 3229.312320500975,
"count": 63718,
"is_parallel": true,
"self": 1421.4461987319253,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003097539999998844,
"count": 1,
"is_parallel": true,
"self": 0.0010886029999710445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020089370000277995,
"count": 8,
"is_parallel": true,
"self": 0.0020089370000277995
}
}
},
"UnityEnvironment.step": {
"total": 0.1057899830000224,
"count": 1,
"is_parallel": true,
"self": 0.0006736879997788492,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005328960000952065,
"count": 1,
"is_parallel": true,
"self": 0.0005328960000952065
},
"communicator.exchange": {
"total": 0.10270576800007802,
"count": 1,
"is_parallel": true,
"self": 0.10270576800007802
},
"steps_from_proto": {
"total": 0.0018776310000703234,
"count": 1,
"is_parallel": true,
"self": 0.00041399800011276966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014636329999575537,
"count": 8,
"is_parallel": true,
"self": 0.0014636329999575537
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1807.8661217690499,
"count": 63717,
"is_parallel": true,
"self": 44.882322545129,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 30.729523035890224,
"count": 63717,
"is_parallel": true,
"self": 30.729523035890224
},
"communicator.exchange": {
"total": 1604.382195116066,
"count": 63717,
"is_parallel": true,
"self": 1604.382195116066
},
"steps_from_proto": {
"total": 127.87208107196466,
"count": 63717,
"is_parallel": true,
"self": 27.591135761022542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 100.28094531094212,
"count": 509736,
"is_parallel": true,
"self": 100.28094531094212
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1075.17050321702,
"count": 63718,
"self": 4.59222245906949,
"children": {
"process_trajectory": {
"total": 163.2101811769544,
"count": 63718,
"self": 162.8269295019545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3832516749998831,
"count": 2,
"self": 0.3832516749998831
}
}
},
"_update_policy": {
"total": 907.3680995809962,
"count": 451,
"self": 356.2543030929701,
"children": {
"TorchPPOOptimizer.update": {
"total": 551.1137964880261,
"count": 22743,
"self": 551.1137964880261
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.830000635702163e-07,
"count": 1,
"self": 9.830000635702163e-07
},
"TrainerController._save_models": {
"total": 0.07896630699997331,
"count": 1,
"self": 0.0017642259999774978,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07720208099999581,
"count": 1,
"self": 0.07720208099999581
}
}
}
}
}
}
}