|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Walker.Policy.Entropy.mean": { |
|
"value": 0.9751701951026917, |
|
"min": 0.9748876690864563, |
|
"max": 1.0785539150238037, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.Entropy.sum": { |
|
"value": 30191.26953125, |
|
"min": 27402.6640625, |
|
"max": 34080.0546875, |
|
"count": 84 |
|
}, |
|
"Walker.Environment.EpisodeLength.mean": { |
|
"value": 386.0, |
|
"min": 219.69402985074626, |
|
"max": 472.8225806451613, |
|
"count": 84 |
|
}, |
|
"Walker.Environment.EpisodeLength.sum": { |
|
"value": 30494.0, |
|
"min": 24082.0, |
|
"max": 30804.0, |
|
"count": 84 |
|
}, |
|
"Walker.Step.mean": { |
|
"value": 7019574.0, |
|
"min": 4529769.0, |
|
"max": 7019574.0, |
|
"count": 84 |
|
}, |
|
"Walker.Step.sum": { |
|
"value": 7019574.0, |
|
"min": 4529769.0, |
|
"max": 7019574.0, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 254.55258178710938, |
|
"min": 180.69607543945312, |
|
"max": 289.08148193359375, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 20109.654296875, |
|
"min": 17136.26171875, |
|
"max": 26677.513671875, |
|
"count": 84 |
|
}, |
|
"Walker.Environment.CumulativeReward.mean": { |
|
"value": 834.2935528694829, |
|
"min": 451.4295769652982, |
|
"max": 1251.17235026821, |
|
"count": 84 |
|
}, |
|
"Walker.Environment.CumulativeReward.sum": { |
|
"value": 65909.19067668915, |
|
"min": 52043.73650300503, |
|
"max": 78850.28839248419, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.ExtrinsicReward.mean": { |
|
"value": 834.2935528694829, |
|
"min": 451.4295769652982, |
|
"max": 1251.17235026821, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.ExtrinsicReward.sum": { |
|
"value": 65909.19067668915, |
|
"min": 52043.73650300503, |
|
"max": 78850.28839248419, |
|
"count": 84 |
|
}, |
|
"Walker.Losses.PolicyLoss.mean": { |
|
"value": 0.01623365478978182, |
|
"min": 0.011336696622796202, |
|
"max": 0.023186391922839295, |
|
"count": 84 |
|
}, |
|
"Walker.Losses.PolicyLoss.sum": { |
|
"value": 0.03246730957956364, |
|
"min": 0.011336696622796202, |
|
"max": 0.04033144856027017, |
|
"count": 84 |
|
}, |
|
"Walker.Losses.ValueLoss.mean": { |
|
"value": 1969.206856282552, |
|
"min": 1417.8285481770833, |
|
"max": 2511.2314697265624, |
|
"count": 84 |
|
}, |
|
"Walker.Losses.ValueLoss.sum": { |
|
"value": 3938.413712565104, |
|
"min": 1417.8285481770833, |
|
"max": 4244.896248372395, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.LearningRate.mean": { |
|
"value": 0.00022995061334980333, |
|
"min": 0.00022995061334980333, |
|
"max": 0.0002547353250882299, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.LearningRate.sum": { |
|
"value": 0.00045990122669960665, |
|
"min": 0.00023026640324454, |
|
"max": 0.00050843958052015, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.Epsilon.mean": { |
|
"value": 0.17665019666666673, |
|
"min": 0.17665019666666673, |
|
"max": 0.18491177000000006, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.Epsilon.sum": { |
|
"value": 0.35330039333333346, |
|
"min": 0.17675545999999998, |
|
"max": 0.3694798499999999, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.Beta.mean": { |
|
"value": 0.0038348448136666666, |
|
"min": 0.0038348448136666666, |
|
"max": 0.004247097322999998, |
|
"count": 84 |
|
}, |
|
"Walker.Policy.Beta.sum": { |
|
"value": 0.007669689627333333, |
|
"min": 0.003840097454000001, |
|
"max": 0.008477044515, |
|
"count": 84 |
|
}, |
|
"Walker.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 84 |
|
}, |
|
"Walker.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 84 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1656314245", |
|
"python_version": "3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]", |
|
"command_line_arguments": "D:\\anaconda3\\Scripts\\mlagents-learn config/ppo/Walker.yaml --env=trained-envs-executables/windows/Walker/Walker --run-id=Walker Training --resume", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0", |
|
"numpy_version": "1.23.0", |
|
"end_time_seconds": "1656326420" |
|
}, |
|
"total": 12174.8547253, |
|
"count": 1, |
|
"self": 0.2894927999986976, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.13087020000000038, |
|
"count": 1, |
|
"self": 0.13087020000000038 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 12174.4343623, |
|
"count": 1, |
|
"self": 6.070615599697703, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.2857655, |
|
"count": 1, |
|
"self": 8.2857655 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 12159.726083500304, |
|
"count": 258580, |
|
"self": 6.0408803995997005, |
|
"children": { |
|
"env_step": { |
|
"total": 11360.907780000549, |
|
"count": 258580, |
|
"self": 10549.125928800446, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 807.6818537001556, |
|
"count": 258580, |
|
"self": 22.656972700328993, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 785.0248809998266, |
|
"count": 251984, |
|
"self": 283.48797590012794, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 501.53690509969863, |
|
"count": 251984, |
|
"self": 501.53690509969863 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 4.099997499948191, |
|
"count": 258579, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 12155.932276500014, |
|
"count": 258579, |
|
"is_parallel": true, |
|
"self": 2004.3345526998055, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0008865000000000123, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00020120000000023452, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0006852999999997778, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0006852999999997778 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 10151.596837300209, |
|
"count": 258579, |
|
"is_parallel": true, |
|
"self": 29.771217999668806, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 402.30562069999417, |
|
"count": 258579, |
|
"is_parallel": true, |
|
"self": 402.30562069999417 |
|
}, |
|
"communicator.exchange": { |
|
"total": 9528.911079799947, |
|
"count": 258579, |
|
"is_parallel": true, |
|
"self": 9528.911079799947 |
|
}, |
|
"steps_from_proto": { |
|
"total": 190.60891880059833, |
|
"count": 258579, |
|
"is_parallel": true, |
|
"self": 35.64497170075438, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 154.96394709984395, |
|
"count": 517158, |
|
"is_parallel": true, |
|
"self": 154.96394709984395 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 792.7774231001544, |
|
"count": 258579, |
|
"self": 8.815772700341768, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 293.57826289981256, |
|
"count": 258579, |
|
"self": 292.5119580998129, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.0663047999996706, |
|
"count": 5, |
|
"self": 1.0663047999996706 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 490.3833875, |
|
"count": 121, |
|
"self": 356.30372250004325, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 134.07966499995675, |
|
"count": 3630, |
|
"self": 134.07966499995675 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0999992809956893e-06, |
|
"count": 1, |
|
"self": 1.0999992809956893e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.35189659999923606, |
|
"count": 1, |
|
"self": 0.14961659999789845, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2022800000013376, |
|
"count": 1, |
|
"self": 0.2022800000013376 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |