|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.9973194599151611, |
|
"min": 0.9973194599151611, |
|
"max": 2.8321337699890137, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 9522.40625, |
|
"min": 9522.40625, |
|
"max": 29003.8828125, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.mean": { |
|
"value": 199984.0, |
|
"min": 9952.0, |
|
"max": 199984.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.sum": { |
|
"value": 199984.0, |
|
"min": 9952.0, |
|
"max": 199984.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 12.571406364440918, |
|
"min": 0.47572728991508484, |
|
"max": 12.571406364440918, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2451.42431640625, |
|
"min": 92.29109191894531, |
|
"max": 2509.18017578125, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.mean": { |
|
"value": 199.0, |
|
"min": 199.0, |
|
"max": 199.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.sum": { |
|
"value": 8756.0, |
|
"min": 8756.0, |
|
"max": 10945.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.mean": { |
|
"value": 0.07178010216539761, |
|
"min": 0.0637313820661089, |
|
"max": 0.07344080526495864, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.28712040866159044, |
|
"min": 0.2549255282644356, |
|
"max": 0.3672040263247932, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.20654598974129731, |
|
"min": 0.12228133896247065, |
|
"max": 0.29319270107091644, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.8261839589651893, |
|
"min": 0.4891253558498826, |
|
"max": 1.465963505354582, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 8.082097306000005e-06, |
|
"min": 8.082097306000005e-06, |
|
"max": 0.000291882002706, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 3.232838922400002e-05, |
|
"min": 3.232838922400002e-05, |
|
"max": 0.00138516003828, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.mean": { |
|
"value": 0.10269400000000001, |
|
"min": 0.10269400000000001, |
|
"max": 0.19729400000000002, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.sum": { |
|
"value": 0.41077600000000003, |
|
"min": 0.41077600000000003, |
|
"max": 0.96172, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Beta.mean": { |
|
"value": 0.0001444306000000001, |
|
"min": 0.0001444306000000001, |
|
"max": 0.0048649706, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Beta.sum": { |
|
"value": 0.0005777224000000004, |
|
"min": 0.0005777224000000004, |
|
"max": 0.023089828, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 25.15909090909091, |
|
"min": 3.6818181818181817, |
|
"max": 25.15909090909091, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1107.0, |
|
"min": 162.0, |
|
"max": 1367.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.15909090909091, |
|
"min": 3.6818181818181817, |
|
"max": 25.15909090909091, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1107.0, |
|
"min": 162.0, |
|
"max": 1367.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1674831001", |
|
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1674831423" |
|
}, |
|
"total": 421.75363836500014, |
|
"count": 1, |
|
"self": 0.38647904700019353, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10408978100008426, |
|
"count": 1, |
|
"self": 0.10408978100008426 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 421.26306953699986, |
|
"count": 1, |
|
"self": 0.48244451699656565, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.76575793500001, |
|
"count": 1, |
|
"self": 8.76575793500001 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 411.8989659230035, |
|
"count": 18201, |
|
"self": 0.2573854710267369, |
|
"children": { |
|
"env_step": { |
|
"total": 411.6415804519768, |
|
"count": 18201, |
|
"self": 267.79970916096363, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 143.58499987901723, |
|
"count": 18201, |
|
"self": 1.3773399810045248, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 142.2076598980127, |
|
"count": 18201, |
|
"self": 31.411987064993582, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 110.79567283301913, |
|
"count": 18201, |
|
"self": 110.79567283301913 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.2568714119959168, |
|
"count": 18201, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 420.1027385950172, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 203.42454528402072, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.008102817000008145, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.005751819000352043, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0023509979996561015, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0023509979996561015 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.03583610299983775, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006429459997434606, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00039990000004763715, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00039990000004763715 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.033007839999982025, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.033007839999982025 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017854170000646263, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040712700047151884, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013782899995931075, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0013782899995931075 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 216.67819331099645, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 8.330785176961172, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 4.967091177031534, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 4.967091177031534 |
|
}, |
|
"communicator.exchange": { |
|
"total": 173.281139570988, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 173.281139570988 |
|
}, |
|
"steps_from_proto": { |
|
"total": 30.099177386015754, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 6.405466022087694, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 23.69371136392806, |
|
"count": 182000, |
|
"is_parallel": true, |
|
"self": 23.69371136392806 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 4.344499984654249e-05, |
|
"count": 1, |
|
"self": 4.344499984654249e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 409.0083233629589, |
|
"count": 331081, |
|
"is_parallel": true, |
|
"self": 8.979945045006389, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 235.58501234795108, |
|
"count": 331081, |
|
"is_parallel": true, |
|
"self": 234.89843520295153, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6865771449995464, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.6865771449995464 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 164.44336597000142, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 40.71944720900456, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 123.72391876099687, |
|
"count": 4587, |
|
"is_parallel": true, |
|
"self": 123.72391876099687 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1158577169999262, |
|
"count": 1, |
|
"self": 0.0008093330002338917, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1150483839996923, |
|
"count": 1, |
|
"self": 0.1150483839996923 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |