|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.9512588381767273, |
|
"min": 0.9417502284049988, |
|
"max": 2.8594980239868164, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 9082.619140625, |
|
"min": 9082.619140625, |
|
"max": 29284.119140625, |
|
"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": 12.921613693237305, |
|
"min": 0.3856821656227112, |
|
"max": 12.921613693237305, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2519.714599609375, |
|
"min": 74.82234191894531, |
|
"max": 2609.662109375, |
|
"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": 0.06380407115120404, |
|
"min": 0.06369956933565703, |
|
"max": 0.07639030339908226, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.25521628460481616, |
|
"min": 0.25521628460481616, |
|
"max": 0.3597449353649555, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.18948892493020084, |
|
"min": 0.1073219246714942, |
|
"max": 0.2716270755319034, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.7579556997208033, |
|
"min": 0.4292876986859768, |
|
"max": 1.358135377659517, |
|
"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": 25.545454545454547, |
|
"min": 2.8863636363636362, |
|
"max": 25.545454545454547, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1124.0, |
|
"min": 127.0, |
|
"max": 1381.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.545454545454547, |
|
"min": 2.8863636363636362, |
|
"max": 25.545454545454547, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1124.0, |
|
"min": 127.0, |
|
"max": 1381.0, |
|
"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": "1673617424", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"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": "1673617913" |
|
}, |
|
"total": 489.33900238499996, |
|
"count": 1, |
|
"self": 0.38617692399998305, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11810907100004897, |
|
"count": 1, |
|
"self": 0.11810907100004897 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 488.8347163899999, |
|
"count": 1, |
|
"self": 0.5901308539971524, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.14098250699999, |
|
"count": 1, |
|
"self": 9.14098250699999 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 478.9746991950029, |
|
"count": 18203, |
|
"self": 0.326246008984981, |
|
"children": { |
|
"env_step": { |
|
"total": 478.64845318601795, |
|
"count": 18203, |
|
"self": 314.1683098680205, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 164.16110781899602, |
|
"count": 18203, |
|
"self": 1.5875299109919752, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 162.57357790800404, |
|
"count": 18203, |
|
"self": 37.89299682701278, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 124.68058108099126, |
|
"count": 18203, |
|
"self": 124.68058108099126 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3190354990014157, |
|
"count": 18203, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 487.34373233700387, |
|
"count": 18203, |
|
"is_parallel": true, |
|
"self": 233.7723657629964, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007398588000000927, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003189778000091792, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0042088099999091355, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0042088099999091355 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.03936033499996938, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005579969999871537, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0003169980000166106, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003169980000166106 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.03641383399997267, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.03641383399997267 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002071505999992951, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005089689998385438, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001562537000154407, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.001562537000154407 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 253.57136657400747, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 9.571010491998777, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 5.831028149005988, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 5.831028149005988 |
|
}, |
|
"communicator.exchange": { |
|
"total": 201.86724962301082, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 201.86724962301082 |
|
}, |
|
"steps_from_proto": { |
|
"total": 36.302078309991884, |
|
"count": 18202, |
|
"is_parallel": true, |
|
"self": 8.025969607965408, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 28.276108702026477, |
|
"count": 182020, |
|
"is_parallel": true, |
|
"self": 28.276108702026477 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.247100001630315e-05, |
|
"count": 1, |
|
"self": 9.247100001630315e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 475.33899181899756, |
|
"count": 386602, |
|
"is_parallel": true, |
|
"self": 11.08869557795083, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 272.56053755504706, |
|
"count": 386602, |
|
"is_parallel": true, |
|
"self": 271.7125273090471, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8480102459999443, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.8480102459999443 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 191.68975868599966, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 46.61698767099665, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 145.072771015003, |
|
"count": 4587, |
|
"is_parallel": true, |
|
"self": 145.072771015003 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.12881136299984064, |
|
"count": 1, |
|
"self": 0.0008075499999904423, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1280038129998502, |
|
"count": 1, |
|
"self": 0.1280038129998502 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |