|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.17636123299598694, |
|
"min": 0.1618323028087616, |
|
"max": 1.4840075969696045, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5271.08447265625, |
|
"min": 4847.201171875, |
|
"max": 45018.85546875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999944.0, |
|
"min": 29952.0, |
|
"max": 2999944.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999944.0, |
|
"min": 29952.0, |
|
"max": 2999944.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7393283843994141, |
|
"min": -0.10577838122844696, |
|
"max": 0.8459022045135498, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 214.4052276611328, |
|
"min": -25.492589950561523, |
|
"max": 248.0259552001953, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01535391341894865, |
|
"min": -0.01118565071374178, |
|
"max": 0.25239965319633484, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.452634811401367, |
|
"min": -3.2550244331359863, |
|
"max": 59.81871795654297, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0649298925884068, |
|
"min": 0.06359526192277877, |
|
"max": 0.07724414270180804, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.973948388826102, |
|
"min": 0.5407089989126563, |
|
"max": 1.0741160183268434, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014976527761771446, |
|
"min": 0.00011271288846747772, |
|
"max": 0.017429315878858685, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2246479164265717, |
|
"min": 0.0014652675500772103, |
|
"max": 0.2511187422011668, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.510952829715555e-06, |
|
"min": 1.510952829715555e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.2664292445733325e-05, |
|
"min": 2.2664292445733325e-05, |
|
"max": 0.003758777947074066, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050361777777778, |
|
"min": 0.10050361777777778, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5075542666666666, |
|
"min": 1.3962282666666668, |
|
"max": 2.6775751333333333, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.0311416000000004e-05, |
|
"min": 6.0311416000000004e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00090467124, |
|
"min": 0.00090467124, |
|
"max": 0.12530730074000002, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.004226378630846739, |
|
"min": 0.004078343976289034, |
|
"max": 0.344288170337677, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.0633956789970398, |
|
"min": 0.0576108917593956, |
|
"max": 2.410017251968384, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 242.7731092436975, |
|
"min": 227.74603174603175, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28890.0, |
|
"min": 15984.0, |
|
"max": 32617.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.723909979624053, |
|
"min": -1.0000000521540642, |
|
"max": 1.7693119835853577, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 206.86919755488634, |
|
"min": -31.998401656746864, |
|
"max": 229.18659903109074, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.723909979624053, |
|
"min": -1.0000000521540642, |
|
"max": 1.7693119835853577, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 206.86919755488634, |
|
"min": -31.998401656746864, |
|
"max": 229.18659903109074, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01071105161451366, |
|
"min": 0.010161933993610242, |
|
"max": 7.139139750041068, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.2853261937416391, |
|
"min": 1.222438158802106, |
|
"max": 114.22623600065708, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1670136954", |
|
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670143826" |
|
}, |
|
"total": 6872.862036082, |
|
"count": 1, |
|
"self": 0.46104419299899746, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1203802150000115, |
|
"count": 1, |
|
"self": 0.1203802150000115 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6872.280611674, |
|
"count": 1, |
|
"self": 3.602157347018874, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 11.759970377000002, |
|
"count": 1, |
|
"self": 11.759970377000002 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6856.820304413981, |
|
"count": 194364, |
|
"self": 4.016479257975334, |
|
"children": { |
|
"env_step": { |
|
"total": 4776.593422325084, |
|
"count": 194364, |
|
"self": 4456.65035676106, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 317.6670216709928, |
|
"count": 194364, |
|
"self": 13.3219556679187, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 304.3450660030741, |
|
"count": 187561, |
|
"self": 105.1740392898651, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 199.17102671320902, |
|
"count": 187561, |
|
"self": 199.17102671320902 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.2760438930317264, |
|
"count": 194364, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6859.724609572037, |
|
"count": 194364, |
|
"is_parallel": true, |
|
"self": 2697.771441217068, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.01001343400002952, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.006313529000124163, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003699904999905357, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003699904999905357 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05126570300001276, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004893339999512136, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004791790000240326, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004791790000240326 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04870433500002491, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04870433500002491 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015928550000126052, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004191580000565409, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011736969999560642, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011736969999560642 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4161.9531683549685, |
|
"count": 194363, |
|
"is_parallel": true, |
|
"self": 86.17202615501355, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 68.8161383529087, |
|
"count": 194363, |
|
"is_parallel": true, |
|
"self": 68.8161383529087 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3725.698910520873, |
|
"count": 194363, |
|
"is_parallel": true, |
|
"self": 3725.698910520873 |
|
}, |
|
"steps_from_proto": { |
|
"total": 281.26609332617323, |
|
"count": 194363, |
|
"is_parallel": true, |
|
"self": 65.5788962192118, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 215.68719710696143, |
|
"count": 1554904, |
|
"is_parallel": true, |
|
"self": 215.68719710696143 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2076.2104028309213, |
|
"count": 194364, |
|
"self": 7.2777088008219835, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 460.538006682097, |
|
"count": 194364, |
|
"self": 459.9491172210974, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5888894609995532, |
|
"count": 6, |
|
"self": 0.5888894609995532 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1608.3946873480024, |
|
"count": 1384, |
|
"self": 596.3508853650264, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1012.043801982976, |
|
"count": 68418, |
|
"self": 1012.043801982976 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.440001693088561e-07, |
|
"count": 1, |
|
"self": 8.440001693088561e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09817869200014684, |
|
"count": 1, |
|
"self": 0.0014101900005698553, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09676850199957698, |
|
"count": 1, |
|
"self": 0.09676850199957698 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |