|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3403747081756592, |
|
"min": 0.3351328670978546, |
|
"max": 1.4651857614517212, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 10211.2412109375, |
|
"min": 10031.66796875, |
|
"max": 44447.875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989900.0, |
|
"min": 29952.0, |
|
"max": 989900.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989900.0, |
|
"min": 29952.0, |
|
"max": 989900.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.41625842452049255, |
|
"min": -0.10713835060596466, |
|
"max": 0.4788300693035126, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 113.2222900390625, |
|
"min": -25.820343017578125, |
|
"max": 129.28411865234375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.02030564658343792, |
|
"min": 0.0025852809194475412, |
|
"max": 0.2987021207809448, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.523135662078857, |
|
"min": 0.6799288988113403, |
|
"max": 71.98721313476562, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06674333069948298, |
|
"min": 0.06401750697864055, |
|
"max": 0.07506186475930247, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0011499604922447, |
|
"min": 0.48197702641348655, |
|
"max": 1.0522968240137045, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01788788605336818, |
|
"min": 0.00012401474126342825, |
|
"max": 0.01788788605336818, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2683182908005227, |
|
"min": 0.0011161326713708542, |
|
"max": 0.2683182908005227, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.5010574996799965e-06, |
|
"min": 7.5010574996799965e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011251586249519995, |
|
"min": 0.00011251586249519995, |
|
"max": 0.0031391615536129, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10250032, |
|
"min": 0.10250032, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5375048, |
|
"min": 1.3886848, |
|
"max": 2.4009775, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002597819679999999, |
|
"min": 0.0002597819679999999, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003896729519999999, |
|
"min": 0.003896729519999999, |
|
"max": 0.10466407129000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01351509802043438, |
|
"min": 0.01351509802043438, |
|
"max": 0.4925374984741211, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.20272646844387054, |
|
"min": 0.1916438192129135, |
|
"max": 3.4477624893188477, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 398.89473684210526, |
|
"min": 395.1095890410959, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30316.0, |
|
"min": 15984.0, |
|
"max": 33223.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4694920888072567, |
|
"min": -1.0000000521540642, |
|
"max": 1.5226684704627076, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 111.6813987493515, |
|
"min": -32.000001668930054, |
|
"max": 111.6813987493515, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4694920888072567, |
|
"min": -1.0000000521540642, |
|
"max": 1.5226684704627076, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 111.6813987493515, |
|
"min": -32.000001668930054, |
|
"max": 111.6813987493515, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05644686557015551, |
|
"min": 0.05644686557015551, |
|
"max": 9.308947062119842, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.289961783331819, |
|
"min": 4.289961783331819, |
|
"max": 148.94315299391747, |
|
"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": "1678293616", |
|
"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": "1678295859" |
|
}, |
|
"total": 2243.027940682, |
|
"count": 1, |
|
"self": 0.4752152610003577, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.167412640999828, |
|
"count": 1, |
|
"self": 0.167412640999828 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2242.38531278, |
|
"count": 1, |
|
"self": 1.2878140139755487, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.807704220000005, |
|
"count": 1, |
|
"self": 6.807704220000005 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2234.2034106710244, |
|
"count": 63626, |
|
"self": 1.3855573650735096, |
|
"children": { |
|
"env_step": { |
|
"total": 1493.236300011993, |
|
"count": 63626, |
|
"self": 1383.8195528369438, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 108.63509279794607, |
|
"count": 63626, |
|
"self": 4.623324343899412, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 104.01176845404666, |
|
"count": 62556, |
|
"self": 35.22320555009355, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 68.7885629039531, |
|
"count": 62556, |
|
"self": 68.7885629039531 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7816543771032229, |
|
"count": 63626, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2237.697799709004, |
|
"count": 63626, |
|
"is_parallel": true, |
|
"self": 966.0252761590239, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0026682879999953, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008496179998473963, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001818670000147904, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001818670000147904 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04650579400004062, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005088280001928069, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004746110000724002, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004746110000724002 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.043977359999871624, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.043977359999871624 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015449949999037926, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003786540005421557, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001166340999361637, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001166340999361637 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1271.67252354998, |
|
"count": 63625, |
|
"is_parallel": true, |
|
"self": 31.04941988598148, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.77753902897871, |
|
"count": 63625, |
|
"is_parallel": true, |
|
"self": 22.77753902897871 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1126.1971392520331, |
|
"count": 63625, |
|
"is_parallel": true, |
|
"self": 1126.1971392520331 |
|
}, |
|
"steps_from_proto": { |
|
"total": 91.64842538298672, |
|
"count": 63625, |
|
"is_parallel": true, |
|
"self": 21.374707700031877, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 70.27371768295484, |
|
"count": 509000, |
|
"is_parallel": true, |
|
"self": 70.27371768295484 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 739.5815532939575, |
|
"count": 63626, |
|
"self": 2.366418566958373, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 160.4090771319943, |
|
"count": 63626, |
|
"self": 160.2286932429938, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1803838890004954, |
|
"count": 2, |
|
"self": 0.1803838890004954 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 576.8060575950049, |
|
"count": 436, |
|
"self": 225.33555462400113, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 351.4705029710037, |
|
"count": 22833, |
|
"self": 351.4705029710037 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.819997674436308e-07, |
|
"count": 1, |
|
"self": 8.819997674436308e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08638299299991559, |
|
"count": 1, |
|
"self": 0.0013951260002613708, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08498786699965422, |
|
"count": 1, |
|
"self": 0.08498786699965422 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |