giuseppemassafra's picture
First Push
da62f39
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0579770803451538,
"min": 1.0579770803451538,
"max": 2.8730504512786865,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10089.927734375,
"min": 10089.927734375,
"max": 29422.91015625,
"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": 12.63623046875,
"min": 0.2670212388038635,
"max": 12.63623046875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2464.06494140625,
"min": 51.802120208740234,
"max": 2546.85546875,
"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": 0.0697163159467677,
"min": 0.06340836184476667,
"max": 0.07731203519848778,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2788652637870708,
"min": 0.2536334473790667,
"max": 0.3733509651798408,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22931737262828678,
"min": 0.11389053152764544,
"max": 0.2780114304785635,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9172694905131471,
"min": 0.4555621261105818,
"max": 1.3900571523928176,
"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": 24.568181818181817,
"min": 3.409090909090909,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1081.0,
"min": 150.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.568181818181817,
"min": 3.409090909090909,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1081.0,
"min": 150.0,
"max": 1388.0,
"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": "1690277947",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690278440"
},
"total": 493.221551035,
"count": 1,
"self": 0.588354018000075,
"children": {
"run_training.setup": {
"total": 0.053484368999988874,
"count": 1,
"self": 0.053484368999988874
},
"TrainerController.start_learning": {
"total": 492.57971264799994,
"count": 1,
"self": 0.5697354039969014,
"children": {
"TrainerController._reset_env": {
"total": 6.397932823000019,
"count": 1,
"self": 6.397932823000019
},
"TrainerController.advance": {
"total": 485.366483652003,
"count": 18218,
"self": 0.284047814002804,
"children": {
"env_step": {
"total": 485.0824358380002,
"count": 18218,
"self": 354.8369597299927,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.95551670400198,
"count": 18218,
"self": 1.8449422669989985,
"children": {
"TorchPolicy.evaluate": {
"total": 128.11057443700298,
"count": 18218,
"self": 128.11057443700298
}
}
},
"workers": {
"total": 0.2899594040055149,
"count": 18218,
"self": 0.0,
"children": {
"worker_root": {
"total": 490.68146748200223,
"count": 18218,
"is_parallel": true,
"self": 235.0780504910034,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006495840000013686,
"count": 1,
"is_parallel": true,
"self": 0.004304193000052692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021916469999609944,
"count": 10,
"is_parallel": true,
"self": 0.0021916469999609944
}
}
},
"UnityEnvironment.step": {
"total": 0.04858075199996392,
"count": 1,
"is_parallel": true,
"self": 0.0006197879999945144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043172499999855063,
"count": 1,
"is_parallel": true,
"self": 0.00043172499999855063
},
"communicator.exchange": {
"total": 0.04548758199996428,
"count": 1,
"is_parallel": true,
"self": 0.04548758199996428
},
"steps_from_proto": {
"total": 0.0020416570000065803,
"count": 1,
"is_parallel": true,
"self": 0.00037076100016975033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00167089599983683,
"count": 10,
"is_parallel": true,
"self": 0.00167089599983683
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.60341699099882,
"count": 18217,
"is_parallel": true,
"self": 10.99282161200557,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.319446474001438,
"count": 18217,
"is_parallel": true,
"self": 5.319446474001438
},
"communicator.exchange": {
"total": 202.90230598399972,
"count": 18217,
"is_parallel": true,
"self": 202.90230598399972
},
"steps_from_proto": {
"total": 36.38884292099209,
"count": 18217,
"is_parallel": true,
"self": 6.693089887966096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.695753033025994,
"count": 182170,
"is_parallel": true,
"self": 29.695753033025994
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000151082000002134,
"count": 1,
"self": 0.000151082000002134,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 481.1803566370316,
"count": 442724,
"is_parallel": true,
"self": 10.562035219045015,
"children": {
"process_trajectory": {
"total": 261.6939120179861,
"count": 442724,
"is_parallel": true,
"self": 259.9314810409861,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7624309770000082,
"count": 4,
"is_parallel": true,
"self": 1.7624309770000082
}
}
},
"_update_policy": {
"total": 208.92440940000046,
"count": 90,
"is_parallel": true,
"self": 87.29682893500001,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.62758046500045,
"count": 4587,
"is_parallel": true,
"self": 121.62758046500045
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.24540968700000576,
"count": 1,
"self": 0.001160340000069482,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24424934699993628,
"count": 1,
"self": 0.24424934699993628
}
}
}
}
}
}
}