Sam017's picture
First Push
f0954cc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8911822438240051,
"min": 0.8480189442634583,
"max": 2.8618626594543457,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8469.7958984375,
"min": 8312.765625,
"max": 29213.89453125,
"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": 13.019059181213379,
"min": 0.3187960088253021,
"max": 13.126315116882324,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2538.716552734375,
"min": 61.84642791748047,
"max": 2677.768310546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06965519440482061,
"min": 0.06320207155705229,
"max": 0.07503413902658412,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27862077761928244,
"min": 0.25280828622820917,
"max": 0.3751706951329206,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.25063097820270297,
"min": 0.11543055962173121,
"max": 0.3104035296276504,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0025239128108119,
"min": 0.46172223848692484,
"max": 1.3764995225504333,
"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": 3.5,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 154.0,
"max": 1427.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.5,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 154.0,
"max": 1427.0,
"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": "1749857102",
"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": "1749857527"
},
"total": 425.67922703499994,
"count": 1,
"self": 0.44324931899996045,
"children": {
"run_training.setup": {
"total": 0.022630285999980515,
"count": 1,
"self": 0.022630285999980515
},
"TrainerController.start_learning": {
"total": 425.21334743,
"count": 1,
"self": 0.34878235300209326,
"children": {
"TrainerController._reset_env": {
"total": 3.3669160489999967,
"count": 1,
"self": 3.3669160489999967
},
"TrainerController.advance": {
"total": 421.41614242199796,
"count": 18192,
"self": 0.3805799270072612,
"children": {
"env_step": {
"total": 303.0221499359941,
"count": 18192,
"self": 232.3326302039909,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.47860156800505,
"count": 18192,
"self": 1.2618131210026604,
"children": {
"TorchPolicy.evaluate": {
"total": 69.21678844700239,
"count": 18192,
"self": 69.21678844700239
}
}
},
"workers": {
"total": 0.21091816399814434,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.79572756399466,
"count": 18192,
"is_parallel": true,
"self": 219.80550030599272,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004818139000008159,
"count": 1,
"is_parallel": true,
"self": 0.0032152310000128637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016029079999952955,
"count": 10,
"is_parallel": true,
"self": 0.0016029079999952955
}
}
},
"UnityEnvironment.step": {
"total": 0.037793784999962554,
"count": 1,
"is_parallel": true,
"self": 0.0006479140000692496,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004039089999423595,
"count": 1,
"is_parallel": true,
"self": 0.0004039089999423595
},
"communicator.exchange": {
"total": 0.0345637440000246,
"count": 1,
"is_parallel": true,
"self": 0.0345637440000246
},
"steps_from_proto": {
"total": 0.0021782179999263462,
"count": 1,
"is_parallel": true,
"self": 0.00041162199977407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017665960001522762,
"count": 10,
"is_parallel": true,
"self": 0.0017665960001522762
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.99022725800194,
"count": 18191,
"is_parallel": true,
"self": 9.819699469987881,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.39597822700739,
"count": 18191,
"is_parallel": true,
"self": 5.39597822700739
},
"communicator.exchange": {
"total": 156.92035147100353,
"count": 18191,
"is_parallel": true,
"self": 156.92035147100353
},
"steps_from_proto": {
"total": 31.854198090003138,
"count": 18191,
"is_parallel": true,
"self": 5.645972644987523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.208225445015614,
"count": 181910,
"is_parallel": true,
"self": 26.208225445015614
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.0134125589966,
"count": 18192,
"self": 0.43246587699127303,
"children": {
"process_trajectory": {
"total": 25.78193147300567,
"count": 18192,
"self": 25.386262381005736,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3956690919999346,
"count": 4,
"self": 0.3956690919999346
}
}
},
"_update_policy": {
"total": 91.79901520899966,
"count": 90,
"self": 38.00771103500119,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.79130417399847,
"count": 4587,
"self": 53.79130417399847
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.600000001024455e-07,
"count": 1,
"self": 8.600000001024455e-07
},
"TrainerController._save_models": {
"total": 0.08150574599994798,
"count": 1,
"self": 0.0008440319999181156,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08066171400002986,
"count": 1,
"self": 0.08066171400002986
}
}
}
}
}
}
}