|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.21759049594402313, |
|
"min": 0.21643652021884918, |
|
"max": 1.4506746530532837, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 6534.677734375, |
|
"min": 6493.095703125, |
|
"max": 44007.66796875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989955.0, |
|
"min": 29952.0, |
|
"max": 989955.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989955.0, |
|
"min": 29952.0, |
|
"max": 989955.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5828856229782104, |
|
"min": -0.09751451760530472, |
|
"max": 0.5872295498847961, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 162.62509155273438, |
|
"min": -23.403484344482422, |
|
"max": 164.81048583984375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.030949678272008896, |
|
"min": 0.0008500521071255207, |
|
"max": 0.21464945375919342, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 8.634960174560547, |
|
"min": 0.23121416568756104, |
|
"max": 51.515869140625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06806533241372865, |
|
"min": 0.06406886617632528, |
|
"max": 0.07275578019575082, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.02097998620593, |
|
"min": 0.5025194726595669, |
|
"max": 1.0489012830657887, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017276543336791093, |
|
"min": 0.0002420773891748837, |
|
"max": 0.017276543336791093, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2591481500518664, |
|
"min": 0.003147006059273488, |
|
"max": 0.2591481500518664, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.464357511913335e-06, |
|
"min": 7.464357511913335e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011196536267870002, |
|
"min": 0.00011196536267870002, |
|
"max": 0.0035080217306595, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1024880866666667, |
|
"min": 0.1024880866666667, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5373213000000006, |
|
"min": 1.3886848, |
|
"max": 2.5693405, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025855985800000004, |
|
"min": 0.00025855985800000004, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0038783978700000004, |
|
"min": 0.0038783978700000004, |
|
"max": 0.11695711595000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011934969574213028, |
|
"min": 0.011663302779197693, |
|
"max": 0.4093915522098541, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.17902454733848572, |
|
"min": 0.1632862389087677, |
|
"max": 2.8657407760620117, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 305.6914893617021, |
|
"min": 305.6914893617021, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28735.0, |
|
"min": 15984.0, |
|
"max": 33214.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6517446611789948, |
|
"min": -1.0000000521540642, |
|
"max": 1.675648923249955, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 155.2639981508255, |
|
"min": -31.996001675724983, |
|
"max": 157.51099878549576, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6517446611789948, |
|
"min": -1.0000000521540642, |
|
"max": 1.675648923249955, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 155.2639981508255, |
|
"min": -31.996001675724983, |
|
"max": 157.51099878549576, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03888845088511787, |
|
"min": 0.03888845088511787, |
|
"max": 8.094916989095509, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.65551438320108, |
|
"min": 3.65551438320108, |
|
"max": 129.51867182552814, |
|
"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": "1687978964", |
|
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1687981230" |
|
}, |
|
"total": 2266.0290720290004, |
|
"count": 1, |
|
"self": 0.4751159620004728, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04153561300017827, |
|
"count": 1, |
|
"self": 0.04153561300017827 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2265.5124204539998, |
|
"count": 1, |
|
"self": 1.6117301190538456, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.9820523250000406, |
|
"count": 1, |
|
"self": 3.9820523250000406 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2259.8210425869456, |
|
"count": 63985, |
|
"self": 1.612149465911898, |
|
"children": { |
|
"env_step": { |
|
"total": 1609.9783523530327, |
|
"count": 63985, |
|
"self": 1488.6854630620144, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 120.3689780320467, |
|
"count": 63985, |
|
"self": 5.1040992891521455, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 115.26487874289455, |
|
"count": 62569, |
|
"self": 115.26487874289455 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9239112589716569, |
|
"count": 63985, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2260.016439649016, |
|
"count": 63985, |
|
"is_parallel": true, |
|
"self": 895.4984385990399, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001846272999955545, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006325659994672606, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012137070004882844, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012137070004882844 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.08021257499990497, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005823470000905218, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005158989999927144, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005158989999927144 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.077333519999911, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.077333519999911 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017808089999107324, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003661049995571375, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001414704000353595, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001414704000353595 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1364.518001049976, |
|
"count": 63984, |
|
"is_parallel": true, |
|
"self": 33.9289768568608, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.873345518046563, |
|
"count": 63984, |
|
"is_parallel": true, |
|
"self": 23.873345518046563 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1198.8350235660218, |
|
"count": 63984, |
|
"is_parallel": true, |
|
"self": 1198.8350235660218 |
|
}, |
|
"steps_from_proto": { |
|
"total": 107.88065510904676, |
|
"count": 63984, |
|
"is_parallel": true, |
|
"self": 21.90715231601871, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 85.97350279302805, |
|
"count": 511872, |
|
"is_parallel": true, |
|
"self": 85.97350279302805 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 648.2305407680012, |
|
"count": 63985, |
|
"self": 2.8762797320075606, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 115.16028934299334, |
|
"count": 63985, |
|
"self": 114.95239166899341, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20789767399992343, |
|
"count": 2, |
|
"self": 0.20789767399992343 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 530.1939716930003, |
|
"count": 453, |
|
"self": 340.0064953820031, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 190.18747631099723, |
|
"count": 22776, |
|
"self": 190.18747631099723 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.350001164420974e-07, |
|
"count": 1, |
|
"self": 9.350001164420974e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0975944880001407, |
|
"count": 1, |
|
"self": 0.0014164540002639114, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09617803399987679, |
|
"count": 1, |
|
"self": 0.09617803399987679 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |