|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.36933454871177673, |
|
"min": 0.36933454871177673, |
|
"max": 1.3809680938720703, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11050.4892578125, |
|
"min": 11050.4892578125, |
|
"max": 41893.046875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989979.0, |
|
"min": 29993.0, |
|
"max": 989979.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989979.0, |
|
"min": 29993.0, |
|
"max": 989979.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5526103973388672, |
|
"min": -0.1131763830780983, |
|
"max": 0.6097274422645569, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 153.0730743408203, |
|
"min": -26.93597984313965, |
|
"max": 173.16259765625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.10367921739816666, |
|
"min": -0.03059101477265358, |
|
"max": 0.3197885751724243, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 28.71914291381836, |
|
"min": -8.014845848083496, |
|
"max": 76.1593017578125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06575524217138688, |
|
"min": 0.06557429362017154, |
|
"max": 0.07262099864892331, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9205733903994163, |
|
"min": 0.5506743529571609, |
|
"max": 1.0456874204043973, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01591464868743926, |
|
"min": 0.00012599772750685083, |
|
"max": 0.01948653281091925, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22280508162414964, |
|
"min": 0.001637970457589061, |
|
"max": 0.2728114593528695, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.730154566171427e-06, |
|
"min": 7.730154566171427e-06, |
|
"max": 0.00029484978921673756, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010822216392639998, |
|
"min": 0.00010822216392639998, |
|
"max": 0.0036334189888603996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10257668571428571, |
|
"min": 0.10257668571428571, |
|
"max": 0.1982832625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4360736, |
|
"min": 1.4360736, |
|
"max": 2.6111396000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002674109028571429, |
|
"min": 0.0002674109028571429, |
|
"max": 0.00982849792375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00374375264, |
|
"min": 0.00374375264, |
|
"max": 0.12113284603999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010115030221641064, |
|
"min": 0.009766151197254658, |
|
"max": 0.38958582282066345, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14161042869091034, |
|
"min": 0.13921941816806793, |
|
"max": 3.1166865825653076, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 338.1511627906977, |
|
"min": 290.03921568627453, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29081.0, |
|
"min": 16408.0, |
|
"max": 32362.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5688116190045378, |
|
"min": -0.9997677937630685, |
|
"max": 1.6707352816182024, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 134.91779923439026, |
|
"min": -31.99200165271759, |
|
"max": 170.41499872505665, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5688116190045378, |
|
"min": -0.9997677937630685, |
|
"max": 1.6707352816182024, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 134.91779923439026, |
|
"min": -31.99200165271759, |
|
"max": 170.41499872505665, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.035788601822745014, |
|
"min": 0.030171945635897025, |
|
"max": 7.228043296757867, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.077819756756071, |
|
"min": 3.0545805321016815, |
|
"max": 122.87673604488373, |
|
"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": "1676073074", |
|
"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": "1.21.6", |
|
"end_time_seconds": "1676075369" |
|
}, |
|
"total": 2294.774936077, |
|
"count": 1, |
|
"self": 0.8758720039995751, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11094726900000751, |
|
"count": 1, |
|
"self": 0.11094726900000751 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2293.7881168040003, |
|
"count": 1, |
|
"self": 1.358044972929747, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.3082881259999795, |
|
"count": 1, |
|
"self": 7.3082881259999795 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2284.98848127107, |
|
"count": 63912, |
|
"self": 1.4102717440932793, |
|
"children": { |
|
"env_step": { |
|
"total": 1543.4755689980223, |
|
"count": 63912, |
|
"self": 1426.9630977079244, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 115.66885675099184, |
|
"count": 63912, |
|
"self": 4.757155444005093, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 110.91170130698674, |
|
"count": 62566, |
|
"self": 37.4234579259969, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 73.48824338098984, |
|
"count": 62566, |
|
"self": 73.48824338098984 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8436145391060563, |
|
"count": 63912, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2288.560680921949, |
|
"count": 63912, |
|
"is_parallel": true, |
|
"self": 978.2576164439624, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001954087999820331, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008089499995094229, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001145138000310908, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001145138000310908 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05101084499983699, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006013369998072449, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004926269998577482, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004926269998577482 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.048104286000125285, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.048104286000125285 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018125950000467128, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004442250001375214, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013683699999091914, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013683699999091914 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1310.3030644779865, |
|
"count": 63911, |
|
"is_parallel": true, |
|
"self": 31.217443168883165, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.382087352026247, |
|
"count": 63911, |
|
"is_parallel": true, |
|
"self": 23.382087352026247 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1158.5858962050022, |
|
"count": 63911, |
|
"is_parallel": true, |
|
"self": 1158.5858962050022 |
|
}, |
|
"steps_from_proto": { |
|
"total": 97.11763775207487, |
|
"count": 63911, |
|
"is_parallel": true, |
|
"self": 22.950988836017814, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 74.16664891605706, |
|
"count": 511288, |
|
"is_parallel": true, |
|
"self": 74.16664891605706 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 740.1026405289549, |
|
"count": 63912, |
|
"self": 2.655264900865177, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 165.9031919300944, |
|
"count": 63912, |
|
"self": 165.67025261909453, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.23293931099988185, |
|
"count": 2, |
|
"self": 0.23293931099988185 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 571.5441836979953, |
|
"count": 456, |
|
"self": 222.7690680180133, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 348.77511567998204, |
|
"count": 22782, |
|
"self": 348.77511567998204 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.5669997992517892e-06, |
|
"count": 1, |
|
"self": 1.5669997992517892e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.13330086700034371, |
|
"count": 1, |
|
"self": 0.0018865110005208408, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.13141435599982287, |
|
"count": 1, |
|
"self": 0.13141435599982287 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |