Quangvuisme's picture
First Push
6921574 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7119036316871643,
"min": 0.6735411286354065,
"max": 2.863849401473999,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6765.93212890625,
"min": 6669.6826171875,
"max": 29234.17578125,
"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": 12.97082805633545,
"min": 0.2864246070384979,
"max": 12.97082805633545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2529.3115234375,
"min": 55.566375732421875,
"max": 2639.04541015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06504928311993603,
"min": 0.06123341401792405,
"max": 0.0772246039788668,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26019713247974413,
"min": 0.26019713247974413,
"max": 0.38612301989433395,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1889936936398347,
"min": 0.10487665029416117,
"max": 0.2849218404760548,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7559747745593388,
"min": 0.4195066011766447,
"max": 1.4246092023802739,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.704545454545453,
"min": 3.25,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 143.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.25,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 143.0,
"max": 1404.0,
"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": "1755151273",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1755151704"
},
"total": 431.1269539330001,
"count": 1,
"self": 0.684871485000258,
"children": {
"run_training.setup": {
"total": 0.027246865000051912,
"count": 1,
"self": 0.027246865000051912
},
"TrainerController.start_learning": {
"total": 430.4148355829998,
"count": 1,
"self": 0.3599829300380861,
"children": {
"TrainerController._reset_env": {
"total": 2.868857367000146,
"count": 1,
"self": 2.868857367000146
},
"TrainerController.advance": {
"total": 427.0720314069615,
"count": 18192,
"self": 0.3782031969485615,
"children": {
"env_step": {
"total": 306.91758507198847,
"count": 18192,
"self": 235.72496589002276,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.97102650995748,
"count": 18192,
"self": 1.2839234799903352,
"children": {
"TorchPolicy.evaluate": {
"total": 69.68710302996715,
"count": 18192,
"self": 69.68710302996715
}
}
},
"workers": {
"total": 0.22159267200822796,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 428.8129369079859,
"count": 18192,
"is_parallel": true,
"self": 221.7597887279867,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004717975000176011,
"count": 1,
"is_parallel": true,
"self": 0.0031155190001754818,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016024560000005295,
"count": 10,
"is_parallel": true,
"self": 0.0016024560000005295
}
}
},
"UnityEnvironment.step": {
"total": 0.036432145000162564,
"count": 1,
"is_parallel": true,
"self": 0.000606545000209735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043044800008829043,
"count": 1,
"is_parallel": true,
"self": 0.00043044800008829043
},
"communicator.exchange": {
"total": 0.033455042000014146,
"count": 1,
"is_parallel": true,
"self": 0.033455042000014146
},
"steps_from_proto": {
"total": 0.0019401099998503923,
"count": 1,
"is_parallel": true,
"self": 0.00042746099984469765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015126490000056947,
"count": 10,
"is_parallel": true,
"self": 0.0015126490000056947
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.0531481799992,
"count": 18191,
"is_parallel": true,
"self": 9.974248871003283,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.404289402999211,
"count": 18191,
"is_parallel": true,
"self": 5.404289402999211
},
"communicator.exchange": {
"total": 159.30953556897794,
"count": 18191,
"is_parallel": true,
"self": 159.30953556897794
},
"steps_from_proto": {
"total": 32.36507433701877,
"count": 18191,
"is_parallel": true,
"self": 5.7293703780871965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.635703958931572,
"count": 181910,
"is_parallel": true,
"self": 26.635703958931572
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.77624313802448,
"count": 18192,
"self": 0.4426216210263192,
"children": {
"process_trajectory": {
"total": 27.15790482499733,
"count": 18192,
"self": 26.697965533997376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4599392909999551,
"count": 4,
"self": 0.4599392909999551
}
}
},
"_update_policy": {
"total": 92.17571669200083,
"count": 90,
"self": 37.80042566099951,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.375291031001325,
"count": 4587,
"self": 54.375291031001325
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2989999049750622e-06,
"count": 1,
"self": 1.2989999049750622e-06
},
"TrainerController._save_models": {
"total": 0.11396258000013404,
"count": 1,
"self": 0.0010746670000116865,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11288791300012235,
"count": 1,
"self": 0.11288791300012235
}
}
}
}
}
}
}