ManDag004's picture
First Push
bc648ee verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8655049204826355,
"min": 0.8614604473114014,
"max": 2.8640284538269043,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8225.7587890625,
"min": 8225.7587890625,
"max": 29236.001953125,
"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": 13.094491004943848,
"min": 0.27864256501197815,
"max": 13.094491004943848,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2553.42578125,
"min": 54.05665969848633,
"max": 2646.82080078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06269598000439788,
"min": 0.06185969928250701,
"max": 0.07327726848752183,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25078392001759153,
"min": 0.24743879713002803,
"max": 0.36638634243760915,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1899898076320396,
"min": 0.11400482508664331,
"max": 0.27982764501197666,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7599592305281584,
"min": 0.45601930034657323,
"max": 1.3311954485435111,
"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": 25.818181818181817,
"min": 3.2045454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 141.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.2045454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 141.0,
"max": 1405.0,
"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": "1730525253",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730525690"
},
"total": 437.166352414,
"count": 1,
"self": 0.42555431200003113,
"children": {
"run_training.setup": {
"total": 0.0594708149999974,
"count": 1,
"self": 0.0594708149999974
},
"TrainerController.start_learning": {
"total": 436.681327287,
"count": 1,
"self": 0.34122992499732163,
"children": {
"TrainerController._reset_env": {
"total": 5.288972392000005,
"count": 1,
"self": 5.288972392000005
},
"TrainerController.advance": {
"total": 430.96295379900266,
"count": 18192,
"self": 0.3443709949949607,
"children": {
"env_step": {
"total": 301.23772134100227,
"count": 18192,
"self": 228.7828299099748,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.24436848601579,
"count": 18192,
"self": 1.238767857008611,
"children": {
"TorchPolicy.evaluate": {
"total": 71.00560062900718,
"count": 18192,
"self": 71.00560062900718
}
}
},
"workers": {
"total": 0.21052294501168944,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.2870030270079,
"count": 18192,
"is_parallel": true,
"self": 234.6060127650111,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023951089999627584,
"count": 1,
"is_parallel": true,
"self": 0.0007083120000288545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016867969999339039,
"count": 10,
"is_parallel": true,
"self": 0.0016867969999339039
}
}
},
"UnityEnvironment.step": {
"total": 0.04558369099999027,
"count": 1,
"is_parallel": true,
"self": 0.0007606279999663457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004040059999965706,
"count": 1,
"is_parallel": true,
"self": 0.0004040059999965706
},
"communicator.exchange": {
"total": 0.042090465999990556,
"count": 1,
"is_parallel": true,
"self": 0.042090465999990556
},
"steps_from_proto": {
"total": 0.002328591000036795,
"count": 1,
"is_parallel": true,
"self": 0.0004580610000175511,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018705300000192437,
"count": 10,
"is_parallel": true,
"self": 0.0018705300000192437
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.68099026199684,
"count": 18191,
"is_parallel": true,
"self": 10.010538514997563,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.44828424699989,
"count": 18191,
"is_parallel": true,
"self": 5.44828424699989
},
"communicator.exchange": {
"total": 153.6880982390017,
"count": 18191,
"is_parallel": true,
"self": 153.6880982390017
},
"steps_from_proto": {
"total": 31.534069260997683,
"count": 18191,
"is_parallel": true,
"self": 5.631368322005528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.902700938992155,
"count": 181910,
"is_parallel": true,
"self": 25.902700938992155
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.38086146300543,
"count": 18192,
"self": 0.4185805770051729,
"children": {
"process_trajectory": {
"total": 28.933279571999947,
"count": 18192,
"self": 28.480864641999915,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45241493000003175,
"count": 4,
"self": 0.45241493000003175
}
}
},
"_update_policy": {
"total": 100.02900131400031,
"count": 90,
"self": 41.94939497700216,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.079606336998154,
"count": 4587,
"self": 58.079606336998154
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2739999419864034e-06,
"count": 1,
"self": 1.2739999419864034e-06
},
"TrainerController._save_models": {
"total": 0.08816989700005706,
"count": 1,
"self": 0.0009645820000514504,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08720531500000561,
"count": 1,
"self": 0.08720531500000561
}
}
}
}
}
}
}