Spydurp's picture
First Push
fc5eec6 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.709786593914032,
"min": 0.7051928639411926,
"max": 2.8598363399505615,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6745.81201171875,
"min": 6745.81201171875,
"max": 29193.208984375,
"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": 12.770920753479004,
"min": 0.4690874516963959,
"max": 12.770920753479004,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2490.32958984375,
"min": 91.00296783447266,
"max": 2604.354248046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07111978689014602,
"min": 0.06266354119789493,
"max": 0.07343774249419963,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28447914756058407,
"min": 0.2506541647915797,
"max": 0.3671887124709981,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20227596748108956,
"min": 0.1347506354978381,
"max": 0.27787669353625355,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8091038699243582,
"min": 0.5390025419913524,
"max": 1.2948551169213127,
"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": 25.0,
"min": 3.5681818181818183,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 157.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.5681818181818183,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 157.0,
"max": 1378.0,
"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": "1780547876",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1780548344"
},
"total": 467.4570690790001,
"count": 1,
"self": 0.5905102340001349,
"children": {
"run_training.setup": {
"total": 0.025412581000068712,
"count": 1,
"self": 0.025412581000068712
},
"TrainerController.start_learning": {
"total": 466.8411462639999,
"count": 1,
"self": 0.3769360090010423,
"children": {
"TrainerController._reset_env": {
"total": 2.867700766999974,
"count": 1,
"self": 2.867700766999974
},
"TrainerController.advance": {
"total": 463.48020981599893,
"count": 18192,
"self": 0.4072553809727424,
"children": {
"env_step": {
"total": 340.1231269040128,
"count": 18192,
"self": 265.6899023440021,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.1995422560127,
"count": 18192,
"self": 1.299658247019238,
"children": {
"TorchPolicy.evaluate": {
"total": 72.89988400899347,
"count": 18192,
"self": 72.89988400899347
}
}
},
"workers": {
"total": 0.2336823039979663,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.7518318900038,
"count": 18192,
"is_parallel": true,
"self": 231.64216514101383,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004954522999923938,
"count": 1,
"is_parallel": true,
"self": 0.00349881499971616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014557080002077782,
"count": 10,
"is_parallel": true,
"self": 0.0014557080002077782
}
}
},
"UnityEnvironment.step": {
"total": 0.05297391700003118,
"count": 1,
"is_parallel": true,
"self": 0.0005953009999757342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000445227000000159,
"count": 1,
"is_parallel": true,
"self": 0.000445227000000159
},
"communicator.exchange": {
"total": 0.050105282999993506,
"count": 1,
"is_parallel": true,
"self": 0.050105282999993506
},
"steps_from_proto": {
"total": 0.00182810600006178,
"count": 1,
"is_parallel": true,
"self": 0.00037820199997895543,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014499040000828245,
"count": 10,
"is_parallel": true,
"self": 0.0014499040000828245
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.10966674898998,
"count": 18191,
"is_parallel": true,
"self": 10.524113385985743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.639109370995243,
"count": 18191,
"is_parallel": true,
"self": 5.639109370995243
},
"communicator.exchange": {
"total": 178.27908593099482,
"count": 18191,
"is_parallel": true,
"self": 178.27908593099482
},
"steps_from_proto": {
"total": 38.66735806101417,
"count": 18191,
"is_parallel": true,
"self": 6.6970175990352345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.970340461978935,
"count": 181910,
"is_parallel": true,
"self": 31.970340461978935
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.9498275310134,
"count": 18192,
"self": 0.47313751100352874,
"children": {
"process_trajectory": {
"total": 27.33702424500939,
"count": 18192,
"self": 26.889378442009388,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44764580300000034,
"count": 4,
"self": 0.44764580300000034
}
}
},
"_update_policy": {
"total": 95.13966577500048,
"count": 90,
"self": 38.7001525160058,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.43951325899468,
"count": 4587,
"self": 56.43951325899468
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2279999737074832e-06,
"count": 1,
"self": 1.2279999737074832e-06
},
"TrainerController._save_models": {
"total": 0.11629844399999456,
"count": 1,
"self": 0.0008921879998524673,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1154062560001421,
"count": 1,
"self": 0.1154062560001421
}
}
}
}
}
}
}