PPO-Pyramids / run_logs /timers.json
odiaz1066's picture
Trained Unity ML Agent model on Pyramids
dc1c963
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.34773510694503784,
"min": 0.34773510694503784,
"max": 1.5297305583953857,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10381.9794921875,
"min": 10381.9794921875,
"max": 46405.90625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989988.0,
"min": 29952.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989988.0,
"min": 29952.0,
"max": 989988.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.21132008731365204,
"min": -0.10977562516927719,
"max": 0.2263687252998352,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 54.52058410644531,
"min": -26.016822814941406,
"max": 57.72402572631836,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02578318491578102,
"min": 0.009288961067795753,
"max": 0.4105018377304077,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.652061939239502,
"min": 2.368685007095337,
"max": 97.28893280029297,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07163523948984221,
"min": 0.06405151421397419,
"max": 0.07479183666192743,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.074528592347633,
"min": 0.5149936375459763,
"max": 1.074528592347633,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.009240312760569698,
"min": 0.0004934845176383835,
"max": 0.011129457519668252,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.13860469140854548,
"min": 0.00690878324693737,
"max": 0.15581240527535553,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4192175269599995e-06,
"min": 7.4192175269599995e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011128826290439999,
"min": 0.00011128826290439999,
"max": 0.0035089313303562995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247304,
"min": 0.10247304,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5370956,
"min": 1.3886848,
"max": 2.5696437,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257056696,
"min": 0.000257056696,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038558504400000005,
"min": 0.0038558504400000005,
"max": 0.11698740563000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01490860152989626,
"min": 0.014679391868412495,
"max": 0.539242684841156,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.22362902760505676,
"min": 0.20551148056983948,
"max": 3.7746989727020264,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 617.4489795918367,
"min": 600.5849056603773,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30255.0,
"min": 15984.0,
"max": 33331.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9334897642232933,
"min": -1.0000000521540642,
"max": 0.9592366972748114,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 45.740998446941376,
"min": -29.36300180852413,
"max": 47.00259816646576,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9334897642232933,
"min": -1.0000000521540642,
"max": 0.9592366972748114,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 45.740998446941376,
"min": -29.36300180852413,
"max": 47.00259816646576,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.09300343669376013,
"min": 0.09300343669376013,
"max": 11.539143294095993,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.557168397994246,
"min": 4.367413945452427,
"max": 184.6262927055359,
"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": "1673892511",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "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": "1673894349"
},
"total": 1837.5156951840004,
"count": 1,
"self": 0.42389194600036717,
"children": {
"run_training.setup": {
"total": 0.10389244299994971,
"count": 1,
"self": 0.10389244299994971
},
"TrainerController.start_learning": {
"total": 1836.987910795,
"count": 1,
"self": 1.137877369033049,
"children": {
"TrainerController._reset_env": {
"total": 6.3230999760003215,
"count": 1,
"self": 6.3230999760003215
},
"TrainerController.advance": {
"total": 1829.4419829179665,
"count": 63357,
"self": 1.180744102990957,
"children": {
"env_step": {
"total": 1183.8924413400014,
"count": 63357,
"self": 1086.7623166759222,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.4122276479543,
"count": 63357,
"self": 4.080954949867191,
"children": {
"TorchPolicy.evaluate": {
"total": 92.3312726980871,
"count": 62564,
"self": 31.431484625140456,
"children": {
"TorchPolicy.sample_actions": {
"total": 60.89978807294665,
"count": 62564,
"self": 60.89978807294665
}
}
}
}
},
"workers": {
"total": 0.7178970161248799,
"count": 63357,
"self": 0.0,
"children": {
"worker_root": {
"total": 1832.8096575358309,
"count": 63357,
"is_parallel": true,
"self": 838.1687257837948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017596060001778824,
"count": 1,
"is_parallel": true,
"self": 0.000654450000183715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011051559999941674,
"count": 8,
"is_parallel": true,
"self": 0.0011051559999941674
}
}
},
"UnityEnvironment.step": {
"total": 0.044247270000141725,
"count": 1,
"is_parallel": true,
"self": 0.0005014590005885111,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004533779997473175,
"count": 1,
"is_parallel": true,
"self": 0.0004533779997473175
},
"communicator.exchange": {
"total": 0.04163658099969325,
"count": 1,
"is_parallel": true,
"self": 0.04163658099969325
},
"steps_from_proto": {
"total": 0.0016558520001126453,
"count": 1,
"is_parallel": true,
"self": 0.00044635500034928555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012094969997633598,
"count": 8,
"is_parallel": true,
"self": 0.0012094969997633598
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 994.6409317520361,
"count": 63356,
"is_parallel": true,
"self": 27.1180606330513,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.72340444500196,
"count": 63356,
"is_parallel": true,
"self": 21.72340444500196
},
"communicator.exchange": {
"total": 849.0166226789579,
"count": 63356,
"is_parallel": true,
"self": 849.0166226789579
},
"steps_from_proto": {
"total": 96.7828439950249,
"count": 63356,
"is_parallel": true,
"self": 20.928591776963003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.8542522180619,
"count": 506848,
"is_parallel": true,
"self": 75.8542522180619
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 644.3687974749741,
"count": 63357,
"self": 2.163993647984171,
"children": {
"process_trajectory": {
"total": 140.4274410699859,
"count": 63357,
"self": 140.23733405798657,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19010701199931646,
"count": 2,
"self": 0.19010701199931646
}
}
},
"_update_policy": {
"total": 501.7773627570041,
"count": 453,
"self": 194.08277356294457,
"children": {
"TorchPPOOptimizer.update": {
"total": 307.6945891940595,
"count": 22806,
"self": 307.6945891940595
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.02400008472614e-06,
"count": 1,
"self": 1.02400008472614e-06
},
"TrainerController._save_models": {
"total": 0.08494950800013612,
"count": 1,
"self": 0.0013511520000974997,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08359835600003862,
"count": 1,
"self": 0.08359835600003862
}
}
}
}
}
}
}