neody88's picture
First Push
369a8a1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7623646855354309,
"min": 0.7623646855354309,
"max": 2.8337316513061523,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7245.51416015625,
"min": 7245.51416015625,
"max": 28926.732421875,
"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": 12.544346809387207,
"min": 0.48105770349502563,
"max": 12.599596977233887,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2446.147705078125,
"min": 93.3251953125,
"max": 2570.31787109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06479932968881365,
"min": 0.0638689891938531,
"max": 0.07442304443125156,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2591973187552546,
"min": 0.2554759567754124,
"max": 0.3721152221562578,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18807934027384307,
"min": 0.14138919523433216,
"max": 0.2906801126751245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7523173610953723,
"min": 0.5655567809373286,
"max": 1.4534005633756226,
"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": 24.113636363636363,
"min": 4.045454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1061.0,
"min": 178.0,
"max": 1362.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.113636363636363,
"min": 4.045454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1061.0,
"min": 178.0,
"max": 1362.0,
"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": "1749446863",
"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": "1749447336"
},
"total": 473.17704994199994,
"count": 1,
"self": 0.4390158789999532,
"children": {
"run_training.setup": {
"total": 0.02761081500000273,
"count": 1,
"self": 0.02761081500000273
},
"TrainerController.start_learning": {
"total": 472.710423248,
"count": 1,
"self": 0.4070633970011386,
"children": {
"TrainerController._reset_env": {
"total": 3.997849115000008,
"count": 1,
"self": 3.997849115000008
},
"TrainerController.advance": {
"total": 468.21712305599874,
"count": 18192,
"self": 0.4439395210005159,
"children": {
"env_step": {
"total": 337.4522530089994,
"count": 18192,
"self": 257.3417331449974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.87087315899635,
"count": 18192,
"self": 1.4201879440074663,
"children": {
"TorchPolicy.evaluate": {
"total": 78.45068521498888,
"count": 18192,
"self": 78.45068521498888
}
}
},
"workers": {
"total": 0.2396467050056117,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.1618014009963,
"count": 18192,
"is_parallel": true,
"self": 245.45623023799442,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0066242940000620365,
"count": 1,
"is_parallel": true,
"self": 0.0041785089998711555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002445785000190881,
"count": 10,
"is_parallel": true,
"self": 0.002445785000190881
}
}
},
"UnityEnvironment.step": {
"total": 0.04423654799995802,
"count": 1,
"is_parallel": true,
"self": 0.0007024339998906726,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000926292000031026,
"count": 1,
"is_parallel": true,
"self": 0.000926292000031026
},
"communicator.exchange": {
"total": 0.040337644000032924,
"count": 1,
"is_parallel": true,
"self": 0.040337644000032924
},
"steps_from_proto": {
"total": 0.0022701780000033978,
"count": 1,
"is_parallel": true,
"self": 0.00041449500008639006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018556829999170077,
"count": 10,
"is_parallel": true,
"self": 0.0018556829999170077
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.70557116300188,
"count": 18191,
"is_parallel": true,
"self": 10.731780598996352,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.1397739009901215,
"count": 18191,
"is_parallel": true,
"self": 6.1397739009901215
},
"communicator.exchange": {
"total": 173.1564855070078,
"count": 18191,
"is_parallel": true,
"self": 173.1564855070078
},
"steps_from_proto": {
"total": 35.6775311560076,
"count": 18191,
"is_parallel": true,
"self": 6.457509958011997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.220021197995607,
"count": 181910,
"is_parallel": true,
"self": 29.220021197995607
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 130.32093052599885,
"count": 18192,
"self": 0.5086011499880669,
"children": {
"process_trajectory": {
"total": 30.00805644601064,
"count": 18192,
"self": 29.53458941301062,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4734670330000199,
"count": 4,
"self": 0.4734670330000199
}
}
},
"_update_policy": {
"total": 99.80427293000014,
"count": 90,
"self": 40.712762189003115,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.09151074099702,
"count": 4587,
"self": 59.09151074099702
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1800000265793642e-06,
"count": 1,
"self": 1.1800000265793642e-06
},
"TrainerController._save_models": {
"total": 0.08838650000006965,
"count": 1,
"self": 0.0009171500000775268,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08746934999999212,
"count": 1,
"self": 0.08746934999999212
}
}
}
}
}
}
}