|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5051537156105042, |
|
"min": 0.4853452742099762, |
|
"max": 1.513056993484497, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 15300.095703125, |
|
"min": 14467.171875, |
|
"max": 45900.09765625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989991.0, |
|
"min": 29952.0, |
|
"max": 989991.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989991.0, |
|
"min": 29952.0, |
|
"max": 989991.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.23137111961841583, |
|
"min": -0.10388777405023575, |
|
"max": 0.24372662603855133, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 58.9996337890625, |
|
"min": -25.03695297241211, |
|
"max": 61.662837982177734, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.09272842109203339, |
|
"min": -0.09272842109203339, |
|
"max": 0.1859152466058731, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -23.645748138427734, |
|
"min": -23.645748138427734, |
|
"max": 44.061912536621094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06794592654027622, |
|
"min": 0.06492656937361431, |
|
"max": 0.07365207984583408, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.951242971563867, |
|
"min": 0.4958643328887545, |
|
"max": 1.0615740634093527, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015087230670490368, |
|
"min": 7.437854180035237e-05, |
|
"max": 0.015087230670490368, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21122122938686516, |
|
"min": 0.0010412995852049332, |
|
"max": 0.21122122938686516, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.569504619721429e-06, |
|
"min": 7.569504619721429e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001059730646761, |
|
"min": 0.0001059730646761, |
|
"max": 0.0036090117969960994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10252313571428573, |
|
"min": 0.10252313571428573, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4353239000000002, |
|
"min": 1.3886848, |
|
"max": 2.5696175, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026206125785714293, |
|
"min": 0.00026206125785714293, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036688576100000012, |
|
"min": 0.0036688576100000012, |
|
"max": 0.12031008961000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009150424040853977, |
|
"min": 0.009150424040853977, |
|
"max": 0.2872983515262604, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.12810593843460083, |
|
"min": 0.12810593843460083, |
|
"max": 2.0110883712768555, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 580.7358490566038, |
|
"min": 580.7358490566038, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30779.0, |
|
"min": 15984.0, |
|
"max": 32778.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.9545845849296222, |
|
"min": -1.0000000521540642, |
|
"max": 0.9940782323803591, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 49.63839841634035, |
|
"min": -31.993201658129692, |
|
"max": 49.63839841634035, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.9545845849296222, |
|
"min": -1.0000000521540642, |
|
"max": 0.9940782323803591, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 49.63839841634035, |
|
"min": -31.993201658129692, |
|
"max": 49.63839841634035, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05494384373574016, |
|
"min": 0.05494384373574016, |
|
"max": 5.718502120114863, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.8570798742584884, |
|
"min": 2.7718396679265425, |
|
"max": 91.4960339218378, |
|
"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": "1677163625", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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 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": "1.22.4", |
|
"end_time_seconds": "1677165788" |
|
}, |
|
"total": 2163.157219881, |
|
"count": 1, |
|
"self": 0.4787647240000297, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1057680200001414, |
|
"count": 1, |
|
"self": 0.1057680200001414 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2162.572687137, |
|
"count": 1, |
|
"self": 1.3431537268957072, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.133410075000029, |
|
"count": 1, |
|
"self": 7.133410075000029 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2154.013275158104, |
|
"count": 63316, |
|
"self": 1.4581074859206637, |
|
"children": { |
|
"env_step": { |
|
"total": 1417.1949776481188, |
|
"count": 63316, |
|
"self": 1301.18493342204, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 115.14134002404626, |
|
"count": 63316, |
|
"self": 4.7866251450554955, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 110.35471487899076, |
|
"count": 62565, |
|
"self": 37.233403418031685, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 73.12131146095908, |
|
"count": 62565, |
|
"self": 73.12131146095908 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8687042020324043, |
|
"count": 63316, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2157.643034558964, |
|
"count": 63316, |
|
"is_parallel": true, |
|
"self": 971.4246845159992, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019070739999733632, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000732548999849314, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011745250001240493, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011745250001240493 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04911768900001334, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005699460000414547, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004900690000795294, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004900690000795294 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04637504800007264, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04637504800007264 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016826259998197202, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045430899967868754, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012283170001410326, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012283170001410326 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1186.2183500429646, |
|
"count": 63315, |
|
"is_parallel": true, |
|
"self": 31.16056592801783, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.910829828018677, |
|
"count": 63315, |
|
"is_parallel": true, |
|
"self": 23.910829828018677 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1036.4068679119332, |
|
"count": 63315, |
|
"is_parallel": true, |
|
"self": 1036.4068679119332 |
|
}, |
|
"steps_from_proto": { |
|
"total": 94.74008637499492, |
|
"count": 63315, |
|
"is_parallel": true, |
|
"self": 22.59512137301681, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 72.14496500197811, |
|
"count": 506520, |
|
"is_parallel": true, |
|
"self": 72.14496500197811 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 735.3601900240644, |
|
"count": 63316, |
|
"self": 2.3862093280665704, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 165.39707415499834, |
|
"count": 63316, |
|
"self": 165.20858882199855, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18848533299978953, |
|
"count": 2, |
|
"self": 0.18848533299978953 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 567.5769065409995, |
|
"count": 453, |
|
"self": 218.38905881103437, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 349.18784772996514, |
|
"count": 22806, |
|
"self": 349.18784772996514 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.890000001178123e-07, |
|
"count": 1, |
|
"self": 9.890000001178123e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08284718799995971, |
|
"count": 1, |
|
"self": 0.0015895719998297864, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08125761600012993, |
|
"count": 1, |
|
"self": 0.08125761600012993 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |