|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7765804529190063, |
|
"min": 0.7693268060684204, |
|
"max": 1.4989020824432373, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 23222.861328125, |
|
"min": 23079.8046875, |
|
"max": 45470.6953125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479915.0, |
|
"min": 29952.0, |
|
"max": 479915.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479915.0, |
|
"min": 29952.0, |
|
"max": 479915.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.07533054053783417, |
|
"min": -0.11597465723752975, |
|
"max": -0.027031147852540016, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -18.079330444335938, |
|
"min": -27.83391761779785, |
|
"max": -6.541537761688232, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.022009972482919693, |
|
"min": 0.02092290110886097, |
|
"max": 0.23792162537574768, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.282393455505371, |
|
"min": 5.063342094421387, |
|
"max": 57.10118865966797, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06795522734500267, |
|
"min": 0.06547741769850374, |
|
"max": 0.07149589330930765, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9513731828300374, |
|
"min": 0.48507643652706534, |
|
"max": 1.0338122207869995, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.001875747377896952, |
|
"min": 0.00010847878824929525, |
|
"max": 0.0034901183738337087, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.02626046329055733, |
|
"min": 0.0014102242472408383, |
|
"max": 0.03646642493273125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1134621526585716e-05, |
|
"min": 2.1134621526585716e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0002958847013722, |
|
"min": 0.0002958847013722, |
|
"max": 0.0028548590483804, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10704484285714284, |
|
"min": 0.10704484285714284, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4986277999999997, |
|
"min": 1.3382272, |
|
"max": 2.2507334000000006, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007137798014285714, |
|
"min": 0.0007137798014285714, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00999291722, |
|
"min": 0.00999291722, |
|
"max": 0.09518679804, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.020899411290884018, |
|
"min": 0.020610123872756958, |
|
"max": 0.3443826735019684, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.29259175062179565, |
|
"min": 0.2885417342185974, |
|
"max": 2.4106786251068115, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 976.7096774193549, |
|
"min": 918.4347826086956, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30278.0, |
|
"min": 15984.0, |
|
"max": 32282.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.7837548883211228, |
|
"min": -1.0000000521540642, |
|
"max": -0.48423482801603235, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -24.296401537954807, |
|
"min": -32.000001668930054, |
|
"max": -11.137401044368744, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.7837548883211228, |
|
"min": -1.0000000521540642, |
|
"max": -0.48423482801603235, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -24.296401537954807, |
|
"min": -32.000001668930054, |
|
"max": -11.137401044368744, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.21134806319230026, |
|
"min": 0.20437526276730228, |
|
"max": 6.590765086002648, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.551789958961308, |
|
"min": 6.551789958961308, |
|
"max": 105.45224137604237, |
|
"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": "1672659668", |
|
"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=./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": "1672660579" |
|
}, |
|
"total": 910.968641255, |
|
"count": 1, |
|
"self": 0.5486145940000142, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10780661399996916, |
|
"count": 1, |
|
"self": 0.10780661399996916 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 910.312220047, |
|
"count": 1, |
|
"self": 0.5229745130278616, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.4474684520000665, |
|
"count": 1, |
|
"self": 7.4474684520000665 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 902.240658568972, |
|
"count": 31477, |
|
"self": 0.5624097049468446, |
|
"children": { |
|
"env_step": { |
|
"total": 574.3647021830102, |
|
"count": 31477, |
|
"self": 524.7010023780065, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 49.317611302999126, |
|
"count": 31477, |
|
"self": 2.0492915599936623, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 47.26831974300546, |
|
"count": 31300, |
|
"self": 16.020407565005144, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 31.24791217800032, |
|
"count": 31300, |
|
"self": 31.24791217800032 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.34608850200459074, |
|
"count": 31477, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 908.7484649230188, |
|
"count": 31477, |
|
"is_parallel": true, |
|
"self": 429.708198830013, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.008927554000024429, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0036407360000794142, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.005286817999945015, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.005286817999945015 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0487704989999429, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004930709999371174, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00044277200004216866, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00044277200004216866 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.046261127999969176, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.046261127999969176 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015735279999944396, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004071110001859779, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011664169998084617, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011664169998084617 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 479.0402660930058, |
|
"count": 31476, |
|
"is_parallel": true, |
|
"self": 13.419274207035528, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 10.896192784999812, |
|
"count": 31476, |
|
"is_parallel": true, |
|
"self": 10.896192784999812 |
|
}, |
|
"communicator.exchange": { |
|
"total": 410.0256921869985, |
|
"count": 31476, |
|
"is_parallel": true, |
|
"self": 410.0256921869985 |
|
}, |
|
"steps_from_proto": { |
|
"total": 44.699106913971946, |
|
"count": 31476, |
|
"is_parallel": true, |
|
"self": 10.244900204971714, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 34.45420670900023, |
|
"count": 251808, |
|
"is_parallel": true, |
|
"self": 34.45420670900023 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 327.31354668101494, |
|
"count": 31477, |
|
"self": 0.9240266950100704, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 68.98290329900328, |
|
"count": 31477, |
|
"self": 68.87721640000314, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1056868990001476, |
|
"count": 1, |
|
"self": 0.1056868990001476 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 257.4066166870016, |
|
"count": 208, |
|
"self": 100.13248052000006, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 157.27413616700153, |
|
"count": 11454, |
|
"self": 157.27413616700153 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.129998943535611e-07, |
|
"count": 1, |
|
"self": 9.129998943535611e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10111760000017966, |
|
"count": 1, |
|
"self": 0.0015759160000925476, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09954168400008712, |
|
"count": 1, |
|
"self": 0.09954168400008712 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |