vicbentu's picture
First Push
32ef5dc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9475746154785156,
"min": 0.9475746154785156,
"max": 2.854184627532959,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9005.7490234375,
"min": 9005.7490234375,
"max": 29135.515625,
"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": 11.844703674316406,
"min": 0.3219778835773468,
"max": 11.844703674316406,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2309.71728515625,
"min": 62.463706970214844,
"max": 2386.66455078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06172373725790998,
"min": 0.06172373725790998,
"max": 0.07733792478927581,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24689494903163992,
"min": 0.24689494903163992,
"max": 0.38668962394637907,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18411294999075872,
"min": 0.1358415661299802,
"max": 0.28204228463126163,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7364517999630349,
"min": 0.5433662645199208,
"max": 1.410211423156308,
"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": 23.84090909090909,
"min": 3.6136363636363638,
"max": 23.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1049.0,
"min": 159.0,
"max": 1302.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.84090909090909,
"min": 3.6136363636363638,
"max": 23.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1049.0,
"min": 159.0,
"max": 1302.0,
"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": "1738685036",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738685465"
},
"total": 429.221789918,
"count": 1,
"self": 0.43876622900006623,
"children": {
"run_training.setup": {
"total": 0.023035137999954713,
"count": 1,
"self": 0.023035137999954713
},
"TrainerController.start_learning": {
"total": 428.759988551,
"count": 1,
"self": 0.32698819100096443,
"children": {
"TrainerController._reset_env": {
"total": 2.93882645299999,
"count": 1,
"self": 2.93882645299999
},
"TrainerController.advance": {
"total": 425.37265537499917,
"count": 18192,
"self": 0.3609470729968507,
"children": {
"env_step": {
"total": 301.8391806740015,
"count": 18192,
"self": 230.01079274399632,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.62372435200211,
"count": 18192,
"self": 1.2591809369959037,
"children": {
"TorchPolicy.evaluate": {
"total": 70.36454341500621,
"count": 18192,
"self": 70.36454341500621
}
}
},
"workers": {
"total": 0.20466357800307833,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.09317673200246,
"count": 18192,
"is_parallel": true,
"self": 225.53488973101167,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011896809999996094,
"count": 1,
"is_parallel": true,
"self": 0.010323422999988452,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015733870000076422,
"count": 10,
"is_parallel": true,
"self": 0.0015733870000076422
}
}
},
"UnityEnvironment.step": {
"total": 0.03851842800003169,
"count": 1,
"is_parallel": true,
"self": 0.000627655000073446,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004433879999510282,
"count": 1,
"is_parallel": true,
"self": 0.0004433879999510282
},
"communicator.exchange": {
"total": 0.03550737000000481,
"count": 1,
"is_parallel": true,
"self": 0.03550737000000481
},
"steps_from_proto": {
"total": 0.0019400150000024041,
"count": 1,
"is_parallel": true,
"self": 0.00034578000008878007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001594234999913624,
"count": 10,
"is_parallel": true,
"self": 0.001594234999913624
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 201.5582870009908,
"count": 18191,
"is_parallel": true,
"self": 9.646475848007697,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3567292569844085,
"count": 18191,
"is_parallel": true,
"self": 5.3567292569844085
},
"communicator.exchange": {
"total": 155.13422900000188,
"count": 18191,
"is_parallel": true,
"self": 155.13422900000188
},
"steps_from_proto": {
"total": 31.420852895996802,
"count": 18191,
"is_parallel": true,
"self": 5.579396974994097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.841455921002705,
"count": 181910,
"is_parallel": true,
"self": 25.841455921002705
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.17252762800081,
"count": 18192,
"self": 0.4066930629990111,
"children": {
"process_trajectory": {
"total": 27.327956168001833,
"count": 18192,
"self": 26.630001575001756,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6979545930000768,
"count": 4,
"self": 0.6979545930000768
}
}
},
"_update_policy": {
"total": 95.43787839699996,
"count": 90,
"self": 38.33784339800167,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.1000349989983,
"count": 4587,
"self": 57.1000349989983
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2199999446238508e-06,
"count": 1,
"self": 1.2199999446238508e-06
},
"TrainerController._save_models": {
"total": 0.12151731199992355,
"count": 1,
"self": 0.0009119299999156283,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12060538200000792,
"count": 1,
"self": 0.12060538200000792
}
}
}
}
}
}
}