AntonLu's picture
First Push
4cbc4cd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7605186700820923,
"min": 0.7605186700820923,
"max": 2.867988109588623,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7227.96923828125,
"min": 7227.96923828125,
"max": 29276.423828125,
"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": 13.09015941619873,
"min": 0.24540242552757263,
"max": 13.134605407714844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.5810546875,
"min": 47.608070373535156,
"max": 2675.666259765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07104162995807094,
"min": 0.05976621444346628,
"max": 0.07649089402833602,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28416651983228375,
"min": 0.23906485777386513,
"max": 0.3742212627206326,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20521915313221661,
"min": 0.11634687932240137,
"max": 0.2989635249855472,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8208766125288665,
"min": 0.4653875172896055,
"max": 1.4045535889910716,
"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": 25.772727272727273,
"min": 3.1818181818181817,
"max": 26.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 140.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.1818181818181817,
"max": 26.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 140.0,
"max": 1410.0,
"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": "1751414013",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751414432"
},
"total": 418.6405436360001,
"count": 1,
"self": 0.5626371570001538,
"children": {
"run_training.setup": {
"total": 0.023101914999870132,
"count": 1,
"self": 0.023101914999870132
},
"TrainerController.start_learning": {
"total": 418.05480456400005,
"count": 1,
"self": 0.37202177398671665,
"children": {
"TrainerController._reset_env": {
"total": 3.2205829230001655,
"count": 1,
"self": 3.2205829230001655
},
"TrainerController.advance": {
"total": 414.32910430901325,
"count": 18192,
"self": 0.37769164200904015,
"children": {
"env_step": {
"total": 297.7638494819921,
"count": 18192,
"self": 229.19260293600018,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.3602847669847,
"count": 18192,
"self": 1.250964144990121,
"children": {
"TorchPolicy.evaluate": {
"total": 67.10932062199458,
"count": 18192,
"self": 67.10932062199458
}
}
},
"workers": {
"total": 0.21096177900722068,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.5956302049992,
"count": 18192,
"is_parallel": true,
"self": 215.6093571159713,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006078375000015512,
"count": 1,
"is_parallel": true,
"self": 0.004638040000372712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014403349996428005,
"count": 10,
"is_parallel": true,
"self": 0.0014403349996428005
}
}
},
"UnityEnvironment.step": {
"total": 0.036428031000014016,
"count": 1,
"is_parallel": true,
"self": 0.0006150100000468228,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004322990000673599,
"count": 1,
"is_parallel": true,
"self": 0.0004322990000673599
},
"communicator.exchange": {
"total": 0.033442594000007375,
"count": 1,
"is_parallel": true,
"self": 0.033442594000007375
},
"steps_from_proto": {
"total": 0.0019381279998924583,
"count": 1,
"is_parallel": true,
"self": 0.0004654080003092531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014727199995832052,
"count": 10,
"is_parallel": true,
"self": 0.0014727199995832052
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.98627308902792,
"count": 18191,
"is_parallel": true,
"self": 9.753384701056802,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.404994642986367,
"count": 18191,
"is_parallel": true,
"self": 5.404994642986367
},
"communicator.exchange": {
"total": 154.36849139599622,
"count": 18191,
"is_parallel": true,
"self": 154.36849139599622
},
"steps_from_proto": {
"total": 31.459402348988533,
"count": 18191,
"is_parallel": true,
"self": 5.686022893936979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.773379455051554,
"count": 181910,
"is_parallel": true,
"self": 25.773379455051554
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.1875631850121,
"count": 18192,
"self": 0.4466669809992254,
"children": {
"process_trajectory": {
"total": 26.126163084012887,
"count": 18192,
"self": 25.659892038012686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46627104600020175,
"count": 4,
"self": 0.46627104600020175
}
}
},
"_update_policy": {
"total": 89.61473311999998,
"count": 90,
"self": 37.10161793701104,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.51311518298894,
"count": 4587,
"self": 52.51311518298894
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2800001059076749e-06,
"count": 1,
"self": 1.2800001059076749e-06
},
"TrainerController._save_models": {
"total": 0.13309427799981677,
"count": 1,
"self": 0.0011260409996793896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13196823700013738,
"count": 1,
"self": 0.13196823700013738
}
}
}
}
}
}
}