|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.302870512008667, |
|
"min": 0.302870512008667, |
|
"max": 1.3739312887191772, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9090.9609375, |
|
"min": 9090.9609375, |
|
"max": 41679.578125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989957.0, |
|
"min": 29952.0, |
|
"max": 989957.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989957.0, |
|
"min": 29952.0, |
|
"max": 989957.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5881687998771667, |
|
"min": -0.1194344013929367, |
|
"max": 0.6296327710151672, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 167.62811279296875, |
|
"min": -28.903125762939453, |
|
"max": 181.9638671875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.041804708540439606, |
|
"min": -0.041804708540439606, |
|
"max": 0.4915374219417572, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -11.914341926574707, |
|
"min": -11.914341926574707, |
|
"max": 118.46051788330078, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06601999624191583, |
|
"min": 0.06543748552053522, |
|
"max": 0.07432919119151979, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9242799473868217, |
|
"min": 0.4991180718697115, |
|
"max": 1.1013228439408647, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01646368383011404, |
|
"min": 0.000285531894639079, |
|
"max": 0.019078002878284102, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23049157362159656, |
|
"min": 0.003140850841029869, |
|
"max": 0.26709204029597744, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.626140315128573e-06, |
|
"min": 7.626140315128573e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010676596441180002, |
|
"min": 0.00010676596441180002, |
|
"max": 0.003256915114361699, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10254201428571429, |
|
"min": 0.10254201428571429, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4355882, |
|
"min": 1.3886848, |
|
"max": 2.4846847000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026394722714285726, |
|
"min": 0.00026394722714285726, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003695261180000002, |
|
"min": 0.003695261180000002, |
|
"max": 0.10858526616999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013304063118994236, |
|
"min": 0.013304063118994236, |
|
"max": 0.7025313377380371, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.18625688552856445, |
|
"min": 0.18625688552856445, |
|
"max": 4.91771936416626, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 321.3333333333333, |
|
"min": 282.25688073394497, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29884.0, |
|
"min": 15984.0, |
|
"max": 34213.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6141376106008407, |
|
"min": -1.0000000521540642, |
|
"max": 1.6815927143124016, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 150.11479778587818, |
|
"min": -31.999601677060127, |
|
"max": 184.97519857436419, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6141376106008407, |
|
"min": -1.0000000521540642, |
|
"max": 1.6815927143124016, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 150.11479778587818, |
|
"min": -31.999601677060127, |
|
"max": 184.97519857436419, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.044225466095120146, |
|
"min": 0.04051138887906828, |
|
"max": 13.7274676784873, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.1129683468461735, |
|
"min": 4.1129683468461735, |
|
"max": 219.6394828557968, |
|
"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": "1673368598", |
|
"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": "1673370648" |
|
}, |
|
"total": 2050.213574352, |
|
"count": 1, |
|
"self": 0.536069497999506, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.12103683000009369, |
|
"count": 1, |
|
"self": 0.12103683000009369 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2049.5564680240004, |
|
"count": 1, |
|
"self": 1.222230435070287, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.642377341999918, |
|
"count": 1, |
|
"self": 6.642377341999918 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2041.5963342459304, |
|
"count": 63980, |
|
"self": 1.2707235759476134, |
|
"children": { |
|
"env_step": { |
|
"total": 1366.236088859993, |
|
"count": 63980, |
|
"self": 1263.390075995035, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 102.08838500997376, |
|
"count": 63980, |
|
"self": 4.283972938029365, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 97.8044120719444, |
|
"count": 62560, |
|
"self": 32.938688214999274, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 64.86572385694512, |
|
"count": 62560, |
|
"self": 64.86572385694512 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.757627854984321, |
|
"count": 63980, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2045.786053179052, |
|
"count": 63980, |
|
"is_parallel": true, |
|
"self": 878.2719518130154, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0018910920000507758, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006323230006728409, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001258768999377935, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001258768999377935 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06768031899991911, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005707549998987815, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005024029999276536, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005024029999276536 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06477080500008014, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06477080500008014 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001836356000012529, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004725179996967199, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001363838000315809, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001363838000315809 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1167.5141013660366, |
|
"count": 63979, |
|
"is_parallel": true, |
|
"self": 28.167335601976674, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.705027095946434, |
|
"count": 63979, |
|
"is_parallel": true, |
|
"self": 22.705027095946434 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1023.4573693700534, |
|
"count": 63979, |
|
"is_parallel": true, |
|
"self": 1023.4573693700534 |
|
}, |
|
"steps_from_proto": { |
|
"total": 93.18436929806012, |
|
"count": 63979, |
|
"is_parallel": true, |
|
"self": 22.015982549072987, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 71.16838674898713, |
|
"count": 511832, |
|
"is_parallel": true, |
|
"self": 71.16838674898713 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 674.0895218099897, |
|
"count": 63980, |
|
"self": 2.249337925031341, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 147.7544374419549, |
|
"count": 63980, |
|
"self": 147.5602333419547, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19420410000020638, |
|
"count": 2, |
|
"self": 0.19420410000020638 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 524.0857464430035, |
|
"count": 448, |
|
"self": 200.05483760196125, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 324.0309088410422, |
|
"count": 22821, |
|
"self": 324.0309088410422 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.110000635497272e-07, |
|
"count": 1, |
|
"self": 8.110000635497272e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09552518999998938, |
|
"count": 1, |
|
"self": 0.00133080500017968, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0941943849998097, |
|
"count": 1, |
|
"self": 0.0941943849998097 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |