H-amza's picture
First Push
4e35e22
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8923071026802063,
"min": 0.8923071026802063,
"max": 2.872551441192627,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8519.748046875,
"min": 8519.748046875,
"max": 29480.99609375,
"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": 12.788619041442871,
"min": 0.41576889157295227,
"max": 12.788619041442871,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.78076171875,
"min": 80.65916442871094,
"max": 2589.927734375,
"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": 0.07541149854317636,
"min": 0.06384002663795471,
"max": 0.07541149854317636,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30164599417270543,
"min": 0.26273492237726487,
"max": 0.36839553246881773,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21217459177269654,
"min": 0.11333101776465043,
"max": 0.2934909953790552,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8486983670907862,
"min": 0.45332407105860173,
"max": 1.4408493325406428,
"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": 24.84090909090909,
"min": 3.2954545454545454,
"max": 25.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 145.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.2954545454545454,
"max": 25.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 145.0,
"max": 1379.0,
"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": "1693822247",
"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": "1693822707"
},
"total": 459.64259785,
"count": 1,
"self": 0.43343245599999136,
"children": {
"run_training.setup": {
"total": 0.04694886200002202,
"count": 1,
"self": 0.04694886200002202
},
"TrainerController.start_learning": {
"total": 459.162216532,
"count": 1,
"self": 0.5288670020050859,
"children": {
"TrainerController._reset_env": {
"total": 4.174400598000034,
"count": 1,
"self": 4.174400598000034
},
"TrainerController.advance": {
"total": 454.3228999249949,
"count": 18201,
"self": 0.26550555600226744,
"children": {
"env_step": {
"total": 454.0573943689926,
"count": 18201,
"self": 331.32032703000436,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.45998769200253,
"count": 18201,
"self": 1.811377572003039,
"children": {
"TorchPolicy.evaluate": {
"total": 120.64861011999949,
"count": 18201,
"self": 120.64861011999949
}
}
},
"workers": {
"total": 0.27707964698572596,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.65668536501505,
"count": 18201,
"is_parallel": true,
"self": 217.59511921000728,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006380841000009241,
"count": 1,
"is_parallel": true,
"self": 0.0048593499998332845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015214910001759563,
"count": 10,
"is_parallel": true,
"self": 0.0015214910001759563
}
}
},
"UnityEnvironment.step": {
"total": 0.04743682200000876,
"count": 1,
"is_parallel": true,
"self": 0.0006632629999785422,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003134680000584922,
"count": 1,
"is_parallel": true,
"self": 0.0003134680000584922
},
"communicator.exchange": {
"total": 0.04410161300006621,
"count": 1,
"is_parallel": true,
"self": 0.04410161300006621
},
"steps_from_proto": {
"total": 0.002358477999905517,
"count": 1,
"is_parallel": true,
"self": 0.0004124599998931444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019460180000123728,
"count": 10,
"is_parallel": true,
"self": 0.0019460180000123728
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.06156615500777,
"count": 18200,
"is_parallel": true,
"self": 10.327102608010478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.153863302001469,
"count": 18200,
"is_parallel": true,
"self": 5.153863302001469
},
"communicator.exchange": {
"total": 189.57799721100196,
"count": 18200,
"is_parallel": true,
"self": 189.57799721100196
},
"steps_from_proto": {
"total": 35.002603033993864,
"count": 18200,
"is_parallel": true,
"self": 6.284915213976888,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.717687820016977,
"count": 182000,
"is_parallel": true,
"self": 28.717687820016977
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011661399992135557,
"count": 1,
"self": 0.00011661399992135557,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 451.1093964400078,
"count": 410051,
"is_parallel": true,
"self": 9.151470147021996,
"children": {
"process_trajectory": {
"total": 245.44531724298508,
"count": 410051,
"is_parallel": true,
"self": 244.7153717109851,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7299455319999879,
"count": 4,
"is_parallel": true,
"self": 0.7299455319999879
}
}
},
"_update_policy": {
"total": 196.51260905000072,
"count": 90,
"is_parallel": true,
"self": 78.754067820003,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.75854122999772,
"count": 4587,
"is_parallel": true,
"self": 117.75854122999772
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13593239300007554,
"count": 1,
"self": 0.0008365580000599948,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13509583500001554,
"count": 1,
"self": 0.13509583500001554
}
}
}
}
}
}
}