|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.45588168501853943, |
|
"min": 0.42102205753326416, |
|
"max": 1.4839963912963867, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13698.3330078125, |
|
"min": 12677.81640625, |
|
"max": 45018.515625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989918.0, |
|
"min": 29952.0, |
|
"max": 989918.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989918.0, |
|
"min": 29952.0, |
|
"max": 989918.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.2340034544467926, |
|
"min": -0.09831121563911438, |
|
"max": 0.2542901635169983, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 60.606895446777344, |
|
"min": -23.693002700805664, |
|
"max": 65.09828186035156, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.12898458540439606, |
|
"min": 0.0017850897274911404, |
|
"max": 0.32706183195114136, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 33.40700912475586, |
|
"min": 0.45698297023773193, |
|
"max": 77.51365661621094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07010079346946442, |
|
"min": 0.0654772581436492, |
|
"max": 0.07379807989497499, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9814111085725019, |
|
"min": 0.4785365782724626, |
|
"max": 1.0407467391729974, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015618461425609504, |
|
"min": 0.00022116328993876226, |
|
"max": 0.015618461425609504, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21865845995853306, |
|
"min": 0.0028751227692039093, |
|
"max": 0.21865845995853306, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.401718961364287e-06, |
|
"min": 7.401718961364287e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010362406545910002, |
|
"min": 0.00010362406545910002, |
|
"max": 0.0033821750726084, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246720714285715, |
|
"min": 0.10246720714285715, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4345409, |
|
"min": 1.3691136000000002, |
|
"max": 2.5273916, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025647399357142865, |
|
"min": 0.00025647399357142865, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003590635910000001, |
|
"min": 0.003590635910000001, |
|
"max": 0.11276642083999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012097321450710297, |
|
"min": 0.012097321450710297, |
|
"max": 0.40570780634880066, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.16936250030994415, |
|
"min": 0.16936250030994415, |
|
"max": 2.8399546146392822, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 593.2452830188679, |
|
"min": 550.3921568627451, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31442.0, |
|
"min": 15984.0, |
|
"max": 34038.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.8948444097682282, |
|
"min": -1.0000000521540642, |
|
"max": 1.146271973848343, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 48.32159812748432, |
|
"min": -32.000001668930054, |
|
"max": 57.313598692417145, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.8948444097682282, |
|
"min": -1.0000000521540642, |
|
"max": 1.146271973848343, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 48.32159812748432, |
|
"min": -32.000001668930054, |
|
"max": 57.313598692417145, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.07304160310121477, |
|
"min": 0.0727383116466751, |
|
"max": 7.856110105291009, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.9442465674655978, |
|
"min": 3.7096538939804304, |
|
"max": 125.69776168465614, |
|
"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": "1678986183", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1678988173" |
|
}, |
|
"total": 1989.981309851, |
|
"count": 1, |
|
"self": 0.4242710360001638, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11482838000006268, |
|
"count": 1, |
|
"self": 0.11482838000006268 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1989.4422104349999, |
|
"count": 1, |
|
"self": 1.3494735859542288, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.307940269000028, |
|
"count": 1, |
|
"self": 7.307940269000028 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1980.6810929180456, |
|
"count": 63327, |
|
"self": 1.4212717350133062, |
|
"children": { |
|
"env_step": { |
|
"total": 1350.0454186020127, |
|
"count": 63327, |
|
"self": 1245.1080585559546, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 104.12581197506529, |
|
"count": 63327, |
|
"self": 4.573367906024487, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 99.5524440690408, |
|
"count": 62559, |
|
"self": 99.5524440690408 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8115480709927851, |
|
"count": 63327, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1985.0492919959859, |
|
"count": 63327, |
|
"is_parallel": true, |
|
"self": 851.4864783149274, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0024480590000166558, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006859770001028664, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017620819999137893, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017620819999137893 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04783902400004081, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005273070000839652, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00048051599992504634, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048051599992504634 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04395884200016553, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04395884200016553 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0028723589998662646, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00037813099970662734, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0024942280001596373, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0024942280001596373 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1133.5628136810585, |
|
"count": 63326, |
|
"is_parallel": true, |
|
"self": 30.548956578015122, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.401267630017628, |
|
"count": 63326, |
|
"is_parallel": true, |
|
"self": 22.401267630017628 |
|
}, |
|
"communicator.exchange": { |
|
"total": 990.5919118900031, |
|
"count": 63326, |
|
"is_parallel": true, |
|
"self": 990.5919118900031 |
|
}, |
|
"steps_from_proto": { |
|
"total": 90.02067758302269, |
|
"count": 63326, |
|
"is_parallel": true, |
|
"self": 19.03355787113287, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 70.98711971188982, |
|
"count": 506608, |
|
"is_parallel": true, |
|
"self": 70.98711971188982 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 629.2144025810196, |
|
"count": 63327, |
|
"self": 2.4305180630910854, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 115.92723848093237, |
|
"count": 63327, |
|
"self": 115.72299267893277, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20424580199960474, |
|
"count": 2, |
|
"self": 0.20424580199960474 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 510.85664603699615, |
|
"count": 442, |
|
"self": 328.35290782299967, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 182.50373821399648, |
|
"count": 22848, |
|
"self": 182.50373821399648 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.779996616998687e-07, |
|
"count": 1, |
|
"self": 9.779996616998687e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10370268400038185, |
|
"count": 1, |
|
"self": 0.001457334000406263, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10224534999997559, |
|
"count": 1, |
|
"self": 0.10224534999997559 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |