|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.7936077117919922, |
|
"min": 0.7936077117919922, |
|
"max": 2.8717141151428223, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 7516.2587890625, |
|
"min": 7516.2587890625, |
|
"max": 29693.5234375, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Step.mean": { |
|
"value": 249944.0, |
|
"min": 9952.0, |
|
"max": 249944.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Step.sum": { |
|
"value": 249944.0, |
|
"min": 9952.0, |
|
"max": 249944.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 13.420190811157227, |
|
"min": 0.40915343165397644, |
|
"max": 13.453102111816406, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2603.51708984375, |
|
"min": 79.37576293945312, |
|
"max": 2754.80078125, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.mean": { |
|
"value": 199.0, |
|
"min": 199.0, |
|
"max": 199.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.sum": { |
|
"value": 8756.0, |
|
"min": 8756.0, |
|
"max": 10945.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.mean": { |
|
"value": 0.07382129480091255, |
|
"min": 0.06198602313559283, |
|
"max": 0.07484359238251095, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2952851792036502, |
|
"min": 0.24794409254237132, |
|
"max": 0.37183325733976924, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.1714352320003159, |
|
"min": 0.12650283034114787, |
|
"max": 0.3144377717200447, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.6857409280012636, |
|
"min": 0.5060113213645915, |
|
"max": 1.5721888586002237, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 5.7456980848e-06, |
|
"min": 5.7456980848e-06, |
|
"max": 0.0002935056021648, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 2.29827923392e-05, |
|
"min": 2.29827923392e-05, |
|
"max": 0.0014081280306239997, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.mean": { |
|
"value": 0.10191520000000001, |
|
"min": 0.10191520000000001, |
|
"max": 0.19783520000000002, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.sum": { |
|
"value": 0.40766080000000005, |
|
"min": 0.40766080000000005, |
|
"max": 0.9693760000000002, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.Beta.mean": { |
|
"value": 0.00010556848000000002, |
|
"min": 0.00010556848000000002, |
|
"max": 0.004891976480000001, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.Beta.sum": { |
|
"value": 0.0004222739200000001, |
|
"min": 0.0004222739200000001, |
|
"max": 0.023471862399999998, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 25.977272727272727, |
|
"min": 3.3181818181818183, |
|
"max": 26.545454545454547, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1143.0, |
|
"min": 146.0, |
|
"max": 1460.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.977272727272727, |
|
"min": 3.3181818181818183, |
|
"max": 26.545454545454547, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1143.0, |
|
"min": 146.0, |
|
"max": 1460.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 25 |
|
}, |
|
"SnowballTarget.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 25 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1677279533", |
|
"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": "1.22.4", |
|
"end_time_seconds": "1677280088" |
|
}, |
|
"total": 554.107720699, |
|
"count": 1, |
|
"self": 0.38663874799999576, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11252524500002892, |
|
"count": 1, |
|
"self": 0.11252524500002892 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 553.608556706, |
|
"count": 1, |
|
"self": 0.6053196400019942, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.14332805700002, |
|
"count": 1, |
|
"self": 9.14332805700002 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 543.7421420079979, |
|
"count": 22738, |
|
"self": 0.31340362600667504, |
|
"children": { |
|
"env_step": { |
|
"total": 543.4287383819913, |
|
"count": 22738, |
|
"self": 379.6562143459997, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 163.4536615939926, |
|
"count": 22738, |
|
"self": 1.8098614649817364, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 161.64380012901086, |
|
"count": 22738, |
|
"self": 36.256270307012414, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 125.38752982199844, |
|
"count": 22738, |
|
"self": 125.38752982199844 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.31886244199898783, |
|
"count": 22738, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 551.897024389993, |
|
"count": 22738, |
|
"is_parallel": true, |
|
"self": 270.29963671199914, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006444170000008853, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004630762000033428, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001813407999975425, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.001813407999975425 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05525051600000097, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005474869999488874, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0003983380000249781, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003983380000249781 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05247067700003072, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05247067700003072 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018340139999963867, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000427125000101114, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014068889998952727, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0014068889998952727 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 281.5973876779939, |
|
"count": 22737, |
|
"is_parallel": true, |
|
"self": 11.557764239979463, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 6.334299419994181, |
|
"count": 22737, |
|
"is_parallel": true, |
|
"self": 6.334299419994181 |
|
}, |
|
"communicator.exchange": { |
|
"total": 227.18592594701414, |
|
"count": 22737, |
|
"is_parallel": true, |
|
"self": 227.18592594701414 |
|
}, |
|
"steps_from_proto": { |
|
"total": 36.519398071006094, |
|
"count": 22737, |
|
"is_parallel": true, |
|
"self": 7.850528912001209, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 28.668869159004885, |
|
"count": 227370, |
|
"is_parallel": true, |
|
"self": 28.668869159004885 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 4.098700003396516e-05, |
|
"count": 1, |
|
"self": 4.098700003396516e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 539.7941320780076, |
|
"count": 490518, |
|
"is_parallel": true, |
|
"self": 11.744096337002361, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 306.6125997420049, |
|
"count": 490518, |
|
"is_parallel": true, |
|
"self": 305.3631732810048, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.2494264610000982, |
|
"count": 5, |
|
"is_parallel": true, |
|
"self": 1.2494264610000982 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 221.43743599900034, |
|
"count": 113, |
|
"is_parallel": true, |
|
"self": 84.94256425999811, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 136.49487173900224, |
|
"count": 5760, |
|
"is_parallel": true, |
|
"self": 136.49487173900224 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11772601400002713, |
|
"count": 1, |
|
"self": 0.000871638000035091, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11685437599999204, |
|
"count": 1, |
|
"self": 0.11685437599999204 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |