|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.9304640293121338, |
|
"min": 0.9304640293121338, |
|
"max": 2.864683151245117, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 8884.0703125, |
|
"min": 8884.0703125, |
|
"max": 29368.73046875, |
|
"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": 12.998976707458496, |
|
"min": 0.2619020640850067, |
|
"max": 12.998976707458496, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2534.800537109375, |
|
"min": 50.808998107910156, |
|
"max": 2619.743896484375, |
|
"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": 0.06747290388653603, |
|
"min": 0.05993395472949344, |
|
"max": 0.07371174484918205, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2698916155461441, |
|
"min": 0.2687006451248867, |
|
"max": 0.3505265610589299, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.18791016278898015, |
|
"min": 0.10237762434567856, |
|
"max": 0.2840573507927212, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.7516406511559206, |
|
"min": 0.4095104973827142, |
|
"max": 1.362534106946459, |
|
"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": 26.227272727272727, |
|
"min": 3.1363636363636362, |
|
"max": 26.227272727272727, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1154.0, |
|
"min": 138.0, |
|
"max": 1401.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 26.227272727272727, |
|
"min": 3.1363636363636362, |
|
"max": 26.227272727272727, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1154.0, |
|
"min": 138.0, |
|
"max": 1401.0, |
|
"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": "1691768739", |
|
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
|
"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": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1691769235" |
|
}, |
|
"total": 495.902654257, |
|
"count": 1, |
|
"self": 0.43231169999990016, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.06417416199997206, |
|
"count": 1, |
|
"self": 0.06417416199997206 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 495.4061683950001, |
|
"count": 1, |
|
"self": 0.625945258004208, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.782685975000049, |
|
"count": 1, |
|
"self": 4.782685975000049 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 489.85574652999605, |
|
"count": 18201, |
|
"self": 0.29930609797440866, |
|
"children": { |
|
"env_step": { |
|
"total": 489.55644043202165, |
|
"count": 18201, |
|
"self": 357.241881505007, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 132.0050378849993, |
|
"count": 18201, |
|
"self": 2.1227551020020883, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 129.8822827829972, |
|
"count": 18201, |
|
"self": 129.8822827829972 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3095210420153762, |
|
"count": 18201, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 493.65703140099856, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 230.87760585199783, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00679045499998665, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004348318000097606, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002442136999889044, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.002442136999889044 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05020134799997322, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006146959999568935, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004539369999747578, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004539369999747578 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04686046599999827, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04686046599999827 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0022722490000433027, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003912419999778649, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018810070000654378, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0018810070000654378 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 262.77942554900073, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 10.964830762991937, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 5.753320871014466, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 5.753320871014466 |
|
}, |
|
"communicator.exchange": { |
|
"total": 207.03283610499943, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 207.03283610499943 |
|
}, |
|
"steps_from_proto": { |
|
"total": 39.0284378099949, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 7.226770461008755, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 31.801667348986143, |
|
"count": 182000, |
|
"is_parallel": true, |
|
"self": 31.801667348986143 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.00015703499980190827, |
|
"count": 1, |
|
"self": 0.00015703499980190827, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 486.08100372899867, |
|
"count": 454345, |
|
"is_parallel": true, |
|
"self": 10.3427104750142, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 266.2322346979846, |
|
"count": 454345, |
|
"is_parallel": true, |
|
"self": 264.2243464219847, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 2.0078882759999033, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 2.0078882759999033 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 209.50605855599986, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 82.39957589800974, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 127.10648265799011, |
|
"count": 4584, |
|
"is_parallel": true, |
|
"self": 127.10648265799011 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1416335970000091, |
|
"count": 1, |
|
"self": 0.0008213480000449636, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.14081224899996414, |
|
"count": 1, |
|
"self": 0.14081224899996414 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |