|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 1.005699634552002, |
|
"min": 1.0049445629119873, |
|
"max": 2.8581583499908447, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 9602.419921875, |
|
"min": 9602.419921875, |
|
"max": 29238.9609375, |
|
"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": 13.138331413269043, |
|
"min": 0.439153254032135, |
|
"max": 13.138331413269043, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2561.974609375, |
|
"min": 85.19573211669922, |
|
"max": 2667.48974609375, |
|
"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": 0.06682304018677848, |
|
"min": 0.06318777558472528, |
|
"max": 0.07394380272670269, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2672921607471139, |
|
"min": 0.25275110233890113, |
|
"max": 0.36971901363351345, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.21168423473250633, |
|
"min": 0.15045997612954426, |
|
"max": 0.27696398531689365, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.8467369389300253, |
|
"min": 0.601839904518177, |
|
"max": 1.3848199265844683, |
|
"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": 25.931818181818183, |
|
"min": 3.8636363636363638, |
|
"max": 26.054545454545455, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1141.0, |
|
"min": 170.0, |
|
"max": 1433.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.931818181818183, |
|
"min": 3.8636363636363638, |
|
"max": 26.054545454545455, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1141.0, |
|
"min": 170.0, |
|
"max": 1433.0, |
|
"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": "1674119665", |
|
"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": "1674120112" |
|
}, |
|
"total": 446.43869328599993, |
|
"count": 1, |
|
"self": 0.3915354809999485, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11942846099998405, |
|
"count": 1, |
|
"self": 0.11942846099998405 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 445.927729344, |
|
"count": 1, |
|
"self": 0.6151862049898114, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.883327596000015, |
|
"count": 1, |
|
"self": 9.883327596000015 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 435.30245007401004, |
|
"count": 18202, |
|
"self": 0.3169543530151486, |
|
"children": { |
|
"env_step": { |
|
"total": 434.9854957209949, |
|
"count": 18202, |
|
"self": 287.43907266098716, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 147.24471781000165, |
|
"count": 18202, |
|
"self": 1.4795187950082322, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 145.7651990149934, |
|
"count": 18202, |
|
"self": 33.93978307899471, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 111.8254159359987, |
|
"count": 18202, |
|
"self": 111.8254159359987 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.30170525000607995, |
|
"count": 18202, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 444.54697358399466, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 209.14988695199213, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006653902999971706, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003930167000021356, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0027237359999503497, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0027237359999503497 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.042472591999967335, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00033843799997157475, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0003050390000112202, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003050390000112202 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04001076500003364, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04001076500003364 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018183499999508967, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043609199997263204, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013822579999782647, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0013822579999782647 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 235.39708663200253, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 8.628276847007385, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 5.10889659299437, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 5.10889659299437 |
|
}, |
|
"communicator.exchange": { |
|
"total": 188.46792588100755, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 188.46792588100755 |
|
}, |
|
"steps_from_proto": { |
|
"total": 33.19198731099323, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 6.984772530990767, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 26.20721478000246, |
|
"count": 182010, |
|
"is_parallel": true, |
|
"self": 26.20721478000246 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 5.497300003298733e-05, |
|
"count": 1, |
|
"self": 5.497300003298733e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 432.4641151959673, |
|
"count": 358774, |
|
"is_parallel": true, |
|
"self": 9.394719670966765, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 250.37600252299995, |
|
"count": 358774, |
|
"is_parallel": true, |
|
"self": 249.65628114800006, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.7197213749998923, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.7197213749998923 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 172.69339300200056, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 42.28814319399606, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 130.4052498080045, |
|
"count": 4587, |
|
"is_parallel": true, |
|
"self": 130.4052498080045 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.12671049600010065, |
|
"count": 1, |
|
"self": 0.001004685000111749, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1257058109999889, |
|
"count": 1, |
|
"self": 0.1257058109999889 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |