fangmengling's picture
First Push
77364ea verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7608880996704102,
"min": 0.7608880996704102,
"max": 2.8431344032287598,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7231.48046875,
"min": 7231.48046875,
"max": 29022.71484375,
"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": 12.989102363586426,
"min": 0.458996057510376,
"max": 12.989102363586426,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.875,
"min": 89.04523468017578,
"max": 2624.0185546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07273736500007776,
"min": 0.06208440735188596,
"max": 0.07563457043850612,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.290949460000311,
"min": 0.24833762940754384,
"max": 0.3711134204407013,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19894002947737188,
"min": 0.14710710850297748,
"max": 0.3080141170352113,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7957601179094875,
"min": 0.5884284340119099,
"max": 1.4451664169045053,
"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": 25.568181818181817,
"min": 4.25,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 187.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 4.25,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 187.0,
"max": 1422.0,
"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": "1750235506",
"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": "1750235922"
},
"total": 415.457894194,
"count": 1,
"self": 0.43769542099994396,
"children": {
"run_training.setup": {
"total": 0.02942329100005736,
"count": 1,
"self": 0.02942329100005736
},
"TrainerController.start_learning": {
"total": 414.990775482,
"count": 1,
"self": 0.34275414098021884,
"children": {
"TrainerController._reset_env": {
"total": 3.439257773999998,
"count": 1,
"self": 3.439257773999998
},
"TrainerController.advance": {
"total": 411.12996176501974,
"count": 18192,
"self": 0.3642849520482514,
"children": {
"env_step": {
"total": 294.67282768699647,
"count": 18192,
"self": 226.54689005097293,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.92234287401072,
"count": 18192,
"self": 1.2208699110141197,
"children": {
"TorchPolicy.evaluate": {
"total": 66.7014729629966,
"count": 18192,
"self": 66.7014729629966
}
}
},
"workers": {
"total": 0.20359476201281268,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.7334388019782,
"count": 18192,
"is_parallel": true,
"self": 214.58060474198714,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005425624999929823,
"count": 1,
"is_parallel": true,
"self": 0.0035357450001356483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001889879999794175,
"count": 10,
"is_parallel": true,
"self": 0.001889879999794175
}
}
},
"UnityEnvironment.step": {
"total": 0.034538939999947615,
"count": 1,
"is_parallel": true,
"self": 0.0006505020000986406,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003973349998886988,
"count": 1,
"is_parallel": true,
"self": 0.0003973349998886988
},
"communicator.exchange": {
"total": 0.031214246999979878,
"count": 1,
"is_parallel": true,
"self": 0.031214246999979878
},
"steps_from_proto": {
"total": 0.0022768559999803983,
"count": 1,
"is_parallel": true,
"self": 0.0006752029997869613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001601653000193437,
"count": 10,
"is_parallel": true,
"self": 0.001601653000193437
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 199.15283405999105,
"count": 18191,
"is_parallel": true,
"self": 9.599900660979415,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.283232313006806,
"count": 18191,
"is_parallel": true,
"self": 5.283232313006806
},
"communicator.exchange": {
"total": 153.5421174299953,
"count": 18191,
"is_parallel": true,
"self": 153.5421174299953
},
"steps_from_proto": {
"total": 30.72758365600953,
"count": 18191,
"is_parallel": true,
"self": 5.498115464994271,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.229468191015258,
"count": 181910,
"is_parallel": true,
"self": 25.229468191015258
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.09284912597502,
"count": 18192,
"self": 0.43751134999172336,
"children": {
"process_trajectory": {
"total": 25.749909986983198,
"count": 18192,
"self": 25.315048290983327,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4348616959998708,
"count": 4,
"self": 0.4348616959998708
}
}
},
"_update_policy": {
"total": 89.9054277890001,
"count": 90,
"self": 36.56061625099176,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.344811538008344,
"count": 4587,
"self": 53.344811538008344
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2390000847517513e-06,
"count": 1,
"self": 1.2390000847517513e-06
},
"TrainerController._save_models": {
"total": 0.07880056299995886,
"count": 1,
"self": 0.000835720999930345,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07796484200002851,
"count": 1,
"self": 0.07796484200002851
}
}
}
}
}
}
}