Nvld's picture
First Push
2c0b9b8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8087307214736938,
"min": 0.790695309638977,
"max": 2.8732330799102783,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7686.1767578125,
"min": 7584.349609375,
"max": 29329.962890625,
"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": 13.125731468200684,
"min": 0.5033339858055115,
"max": 13.174393653869629,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.517578125,
"min": 97.64678955078125,
"max": 2700.750732421875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06981715540392791,
"min": 0.05892785134195697,
"max": 0.07441540314363973,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27926862161571164,
"min": 0.2416973086907163,
"max": 0.3720770157181986,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17642045853769078,
"min": 0.10819824809190251,
"max": 0.3044077982651252,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7056818341507631,
"min": 0.43279299236761004,
"max": 1.4620530695891847,
"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": 25.75,
"min": 3.1363636363636362,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 138.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.1363636363636362,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 138.0,
"max": 1418.0,
"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": "1759177885",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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=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": "1759178307"
},
"total": 421.9383013470001,
"count": 1,
"self": 0.7900246230003631,
"children": {
"run_training.setup": {
"total": 0.022807132999787427,
"count": 1,
"self": 0.022807132999787427
},
"TrainerController.start_learning": {
"total": 421.12546959099996,
"count": 1,
"self": 0.3240820320165767,
"children": {
"TrainerController._reset_env": {
"total": 2.91604512899994,
"count": 1,
"self": 2.91604512899994
},
"TrainerController.advance": {
"total": 417.7745739789834,
"count": 18192,
"self": 0.34699338797304335,
"children": {
"env_step": {
"total": 298.60638215200447,
"count": 18192,
"self": 232.2612813510159,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.13968459301213,
"count": 18192,
"self": 1.2015213010265597,
"children": {
"TorchPolicy.evaluate": {
"total": 64.93816329198557,
"count": 18192,
"self": 64.93816329198557
}
}
},
"workers": {
"total": 0.205416207976441,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.1847314569968,
"count": 18192,
"is_parallel": true,
"self": 214.75731718200996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004725108000002365,
"count": 1,
"is_parallel": true,
"self": 0.0032232569994903315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015018510005120334,
"count": 10,
"is_parallel": true,
"self": 0.0015018510005120334
}
}
},
"UnityEnvironment.step": {
"total": 0.034252260000130264,
"count": 1,
"is_parallel": true,
"self": 0.0005666060001203732,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038256899983935,
"count": 1,
"is_parallel": true,
"self": 0.00038256899983935
},
"communicator.exchange": {
"total": 0.03140368200001831,
"count": 1,
"is_parallel": true,
"self": 0.03140368200001831
},
"steps_from_proto": {
"total": 0.0018994030001522333,
"count": 1,
"is_parallel": true,
"self": 0.0003580260004127922,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001541376999739441,
"count": 10,
"is_parallel": true,
"self": 0.001541376999739441
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.42741427498686,
"count": 18191,
"is_parallel": true,
"self": 9.743981884010736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.223954716996559,
"count": 18191,
"is_parallel": true,
"self": 5.223954716996559
},
"communicator.exchange": {
"total": 155.0815129599771,
"count": 18191,
"is_parallel": true,
"self": 155.0815129599771
},
"steps_from_proto": {
"total": 34.377964714002474,
"count": 18191,
"is_parallel": true,
"self": 6.288549863982553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.08941485001992,
"count": 181910,
"is_parallel": true,
"self": 28.08941485001992
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.82119843900591,
"count": 18192,
"self": 0.4031359390050966,
"children": {
"process_trajectory": {
"total": 25.94281958600095,
"count": 18192,
"self": 25.418230179001057,
"children": {
"RLTrainer._checkpoint": {
"total": 0.524589406999894,
"count": 4,
"self": 0.524589406999894
}
}
},
"_update_policy": {
"total": 92.47524291399986,
"count": 90,
"self": 37.93275614000845,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.54248677399141,
"count": 4587,
"self": 54.54248677399141
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3500000477506546e-06,
"count": 1,
"self": 1.3500000477506546e-06
},
"TrainerController._save_models": {
"total": 0.1107671009999649,
"count": 1,
"self": 0.0009115650000239839,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10985553599994091,
"count": 1,
"self": 0.10985553599994091
}
}
}
}
}
}
}