aarongrainer's picture
First Push
75822ce
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8331933617591858,
"min": 0.8331933617591858,
"max": 2.87489652633667,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7955.330078125,
"min": 7955.330078125,
"max": 29410.19140625,
"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": 12.525593757629395,
"min": 0.4189841151237488,
"max": 12.525593757629395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2442.49072265625,
"min": 81.28292083740234,
"max": 2546.746826171875,
"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.Losses.PolicyLoss.mean": {
"value": 0.0672799542009278,
"min": 0.05940197296006897,
"max": 0.07427187424938322,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2691198168037112,
"min": 0.2376078918402759,
"max": 0.3713593712469161,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2382105320838152,
"min": 0.11310969863894998,
"max": 0.29752226641365126,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9528421283352608,
"min": 0.45243879455579994,
"max": 1.4876113320682562,
"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.CumulativeReward.mean": {
"value": 24.681818181818183,
"min": 3.522727272727273,
"max": 24.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 155.0,
"max": 1357.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 3.522727272727273,
"max": 24.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 155.0,
"max": 1357.0,
"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": "1704896475",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704896940"
},
"total": 464.928714938,
"count": 1,
"self": 0.600393793999956,
"children": {
"run_training.setup": {
"total": 0.050673152999934246,
"count": 1,
"self": 0.050673152999934246
},
"TrainerController.start_learning": {
"total": 464.2776479910001,
"count": 1,
"self": 0.6075923019990341,
"children": {
"TrainerController._reset_env": {
"total": 3.26395103699997,
"count": 1,
"self": 3.26395103699997
},
"TrainerController.advance": {
"total": 460.262648056001,
"count": 18201,
"self": 0.2822919660023899,
"children": {
"env_step": {
"total": 459.9803560899986,
"count": 18201,
"self": 301.963590879991,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.72687866501155,
"count": 18201,
"self": 1.527871606000872,
"children": {
"TorchPolicy.evaluate": {
"total": 156.19900705901068,
"count": 18201,
"self": 156.19900705901068
}
}
},
"workers": {
"total": 0.28988654499607946,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.8671964810002,
"count": 18201,
"is_parallel": true,
"self": 230.09420360299578,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005298062999941067,
"count": 1,
"is_parallel": true,
"self": 0.003801401999794507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014966610001465597,
"count": 10,
"is_parallel": true,
"self": 0.0014966610001465597
}
}
},
"UnityEnvironment.step": {
"total": 0.070533044000058,
"count": 1,
"is_parallel": true,
"self": 0.0007043570000178079,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005100270000184537,
"count": 1,
"is_parallel": true,
"self": 0.0005100270000184537
},
"communicator.exchange": {
"total": 0.06734516599999552,
"count": 1,
"is_parallel": true,
"self": 0.06734516599999552
},
"steps_from_proto": {
"total": 0.0019734940000262213,
"count": 1,
"is_parallel": true,
"self": 0.00037617299994963105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015973210000765903,
"count": 10,
"is_parallel": true,
"self": 0.0015973210000765903
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.7729928780044,
"count": 18200,
"is_parallel": true,
"self": 11.121278011993468,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.602552881997553,
"count": 18200,
"is_parallel": true,
"self": 5.602552881997553
},
"communicator.exchange": {
"total": 180.6176618880013,
"count": 18200,
"is_parallel": true,
"self": 180.6176618880013
},
"steps_from_proto": {
"total": 35.43150009601209,
"count": 18200,
"is_parallel": true,
"self": 6.609358316001817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.82214178001027,
"count": 182000,
"is_parallel": true,
"self": 28.82214178001027
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000257859999919674,
"count": 1,
"self": 0.000257859999919674,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.42444028204216,
"count": 682615,
"is_parallel": true,
"self": 15.523125548077928,
"children": {
"process_trajectory": {
"total": 250.74516214396374,
"count": 682615,
"is_parallel": true,
"self": 250.1677714549636,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5773906890001399,
"count": 4,
"is_parallel": true,
"self": 0.5773906890001399
}
}
},
"_update_policy": {
"total": 188.1561525900005,
"count": 90,
"is_parallel": true,
"self": 58.825392000004854,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.33076058999563,
"count": 4587,
"is_parallel": true,
"self": 129.33076058999563
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14319873600015853,
"count": 1,
"self": 0.0013878920001388906,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14181084400001964,
"count": 1,
"self": 0.14181084400001964
}
}
}
}
}
}
}