PeKaChan's picture
First Push
c8af3c3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.766217052936554,
"min": 0.766217052936554,
"max": 0.9099082946777344,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7821.5439453125,
"min": 7362.5,
"max": 9288.34375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 399968.0,
"min": 209936.0,
"max": 399968.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 399968.0,
"min": 209936.0,
"max": 399968.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.461583137512207,
"min": 12.93759536743164,
"max": 13.690086364746094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2625.0087890625,
"min": 2509.893798828125,
"max": 2752.64404296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06564069362517044,
"min": 0.06365411917078531,
"max": 0.0730667203774347,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2625627745006818,
"min": 0.25461647668314125,
"max": 0.36533360188717345,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1894227970464557,
"min": 0.1727855612396025,
"max": 0.22284169090619566,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7576911881858228,
"min": 0.69114224495841,
"max": 1.0255650439683128,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.957098681000002e-06,
"min": 3.957098681000002e-06,
"max": 0.000145857051381,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.582839472400001e-05,
"min": 1.582839472400001e-05,
"max": 0.00069216026928,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101319,
"min": 0.101319,
"max": 0.14861900000000003,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.405276,
"min": 0.405276,
"max": 0.73072,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.581810000000006e-05,
"min": 7.581810000000006e-05,
"max": 0.0024360881000000003,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00030327240000000024,
"min": 0.00030327240000000024,
"max": 0.011562928000000002,
"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": 26.25,
"min": 25.34090909090909,
"max": 26.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1155.0,
"min": 1115.0,
"max": 1464.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.25,
"min": 25.34090909090909,
"max": 26.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1155.0,
"min": 1115.0,
"max": 1464.0,
"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": "1771676966",
"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 --resume",
"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": "1771677383"
},
"total": 416.913193332,
"count": 1,
"self": 0.4765205449998575,
"children": {
"run_training.setup": {
"total": 0.023261899000090125,
"count": 1,
"self": 0.023261899000090125
},
"TrainerController.start_learning": {
"total": 416.41341088800004,
"count": 1,
"self": 0.29849677499692007,
"children": {
"TrainerController._reset_env": {
"total": 2.674031204999892,
"count": 1,
"self": 2.674031204999892
},
"TrainerController.advance": {
"total": 413.36379137400377,
"count": 18192,
"self": 0.3277293529865801,
"children": {
"env_step": {
"total": 297.46436510701164,
"count": 18192,
"self": 231.43444144704154,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.83460441398165,
"count": 18192,
"self": 1.1595606019791376,
"children": {
"TorchPolicy.evaluate": {
"total": 64.67504381200251,
"count": 18192,
"self": 64.67504381200251
}
}
},
"workers": {
"total": 0.19531924598845762,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 414.47013174698645,
"count": 18192,
"is_parallel": true,
"self": 210.66700704497498,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00283743099998901,
"count": 1,
"is_parallel": true,
"self": 0.0007631460002812673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002074284999707743,
"count": 10,
"is_parallel": true,
"self": 0.002074284999707743
}
}
},
"UnityEnvironment.step": {
"total": 0.06919496499995148,
"count": 1,
"is_parallel": true,
"self": 0.0005631349997656798,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040848699995876814,
"count": 1,
"is_parallel": true,
"self": 0.00040848699995876814
},
"communicator.exchange": {
"total": 0.06455294300008063,
"count": 1,
"is_parallel": true,
"self": 0.06455294300008063
},
"steps_from_proto": {
"total": 0.003670400000146401,
"count": 1,
"is_parallel": true,
"self": 0.00035856100021192105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00331183899993448,
"count": 10,
"is_parallel": true,
"self": 0.00331183899993448
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.80312470201147,
"count": 18191,
"is_parallel": true,
"self": 9.750305788005335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.091073207016734,
"count": 18191,
"is_parallel": true,
"self": 5.091073207016734
},
"communicator.exchange": {
"total": 155.38686141598896,
"count": 18191,
"is_parallel": true,
"self": 155.38686141598896
},
"steps_from_proto": {
"total": 33.574884291000444,
"count": 18191,
"is_parallel": true,
"self": 6.094392830025981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.480491460974463,
"count": 181910,
"is_parallel": true,
"self": 27.480491460974463
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.57169691400554,
"count": 18192,
"self": 0.37567183100327384,
"children": {
"process_trajectory": {
"total": 24.759450798003172,
"count": 18192,
"self": 24.4219184290032,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3375323689999732,
"count": 4,
"self": 0.3375323689999732
}
}
},
"_update_policy": {
"total": 90.4365742849991,
"count": 90,
"self": 36.015253016992574,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.42132126800652,
"count": 4587,
"self": 54.42132126800652
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.169998520519584e-07,
"count": 1,
"self": 9.169998520519584e-07
},
"TrainerController._save_models": {
"total": 0.0770906169996124,
"count": 1,
"self": 0.0009243509994121268,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07616626600020027,
"count": 1,
"self": 0.07616626600020027
}
}
}
}
}
}
}