|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.19130906462669373, |
|
"min": 0.17553268373012543, |
|
"max": 1.483086109161377, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5659.6875, |
|
"min": 5240.70361328125, |
|
"max": 44990.8984375, |
|
"count": 86 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2579996.0, |
|
"min": 29952.0, |
|
"max": 2579996.0, |
|
"count": 86 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2579996.0, |
|
"min": 29952.0, |
|
"max": 2579996.0, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8240099549293518, |
|
"min": -0.10620949417352676, |
|
"max": 0.886141300201416, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 249.67501831054688, |
|
"min": -25.59648895263672, |
|
"max": 274.70379638671875, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0140521926805377, |
|
"min": -0.010541483759880066, |
|
"max": 0.3994080126285553, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.257814407348633, |
|
"min": -2.846200704574585, |
|
"max": 94.65969848632812, |
|
"count": 86 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06674559654786835, |
|
"min": 0.06373497846791344, |
|
"max": 0.07371800786256986, |
|
"count": 86 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9344383516701569, |
|
"min": 0.505506548982956, |
|
"max": 1.0904909626891215, |
|
"count": 86 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01545798972877413, |
|
"min": 0.0003068518053494721, |
|
"max": 0.0170064264398423, |
|
"count": 86 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21641185620283782, |
|
"min": 0.003989073469543137, |
|
"max": 0.2436941318252745, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 4.356361405025239e-05, |
|
"min": 4.356361405025239e-05, |
|
"max": 0.00029838354339596195, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0006098905967035335, |
|
"min": 0.0006098905967035335, |
|
"max": 0.003800859533046867, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1145211761904762, |
|
"min": 0.1145211761904762, |
|
"max": 0.19946118095238097, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.603296466666667, |
|
"min": 1.3962282666666668, |
|
"max": 2.7524795999999996, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0014606655014285717, |
|
"min": 0.0014606655014285717, |
|
"max": 0.009946171977142856, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.020449317020000003, |
|
"min": 0.020449317020000003, |
|
"max": 0.12670861802, |
|
"count": 86 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007880064658820629, |
|
"min": 0.007141666021198034, |
|
"max": 0.3941015303134918, |
|
"count": 86 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11032091081142426, |
|
"min": 0.0999833270907402, |
|
"max": 2.7587106227874756, |
|
"count": 86 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 207.88148148148147, |
|
"min": 207.88148148148147, |
|
"max": 999.0, |
|
"count": 86 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28064.0, |
|
"min": 15984.0, |
|
"max": 32481.0, |
|
"count": 86 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7921193945986122, |
|
"min": -1.0000000521540642, |
|
"max": 1.7921193945986122, |
|
"count": 86 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 240.14399887621403, |
|
"min": -31.995601639151573, |
|
"max": 263.2419985830784, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7921193945986122, |
|
"min": -1.0000000521540642, |
|
"max": 1.7921193945986122, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 240.14399887621403, |
|
"min": -31.995601639151573, |
|
"max": 263.2419985830784, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.017095780673822555, |
|
"min": 0.017095780673822555, |
|
"max": 7.385909885168076, |
|
"count": 86 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.2908346102922224, |
|
"min": 2.078473886853317, |
|
"max": 118.17455816268921, |
|
"count": 86 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 86 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 86 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657744731", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \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": "1657750711" |
|
}, |
|
"total": 5980.278680743, |
|
"count": 1, |
|
"self": 0.42508442800135526, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0426390210000136, |
|
"count": 1, |
|
"self": 0.0426390210000136 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 5979.810957293999, |
|
"count": 1, |
|
"self": 4.7630246399294265, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.02668748200017, |
|
"count": 1, |
|
"self": 10.02668748200017 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 5964.86891988607, |
|
"count": 168734, |
|
"self": 4.845684374235134, |
|
"children": { |
|
"env_step": { |
|
"total": 4081.294303208959, |
|
"count": 168734, |
|
"self": 3769.118829394134, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 309.64846007101346, |
|
"count": 168734, |
|
"self": 13.331629374792556, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 296.3168306962209, |
|
"count": 162701, |
|
"self": 103.58203225335706, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 192.73479844286385, |
|
"count": 162701, |
|
"self": 192.73479844286385 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.5270137438114944, |
|
"count": 168733, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 5967.984283284089, |
|
"count": 168733, |
|
"is_parallel": true, |
|
"self": 2502.1299474501184, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007898622000084288, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.006707159000143292, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011914629999409954, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011914629999409954 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04561361400010355, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005194249997657607, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004514690001542476, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004514690001542476 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.043020894000164844, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.043020894000164844 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016218260000187001, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00041651299989098334, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012053130001277168, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012053130001277168 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3465.8543358339703, |
|
"count": 168732, |
|
"is_parallel": true, |
|
"self": 79.32340474307784, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 62.74795037784088, |
|
"count": 168732, |
|
"is_parallel": true, |
|
"self": 62.74795037784088 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3068.720157017121, |
|
"count": 168732, |
|
"is_parallel": true, |
|
"self": 3068.720157017121 |
|
}, |
|
"steps_from_proto": { |
|
"total": 255.06282369593055, |
|
"count": 168732, |
|
"is_parallel": true, |
|
"self": 66.5604769629465, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 188.50234673298405, |
|
"count": 1349856, |
|
"is_parallel": true, |
|
"self": 188.50234673298405 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1878.7289323028767, |
|
"count": 168733, |
|
"self": 8.850312633996055, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 442.49058333387006, |
|
"count": 168733, |
|
"self": 441.85932786387025, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6312554699998145, |
|
"count": 5, |
|
"self": 0.6312554699998145 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1427.3880363350106, |
|
"count": 1204, |
|
"self": 563.4498628769941, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 863.9381734580165, |
|
"count": 59325, |
|
"self": 863.9381734580165 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.5690002328483388e-06, |
|
"count": 1, |
|
"self": 1.5690002328483388e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.15232371699949, |
|
"count": 1, |
|
"self": 0.0022032189999663387, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.15012049799952365, |
|
"count": 1, |
|
"self": 0.15012049799952365 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |