jwalley's picture
First Push
60e9066
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9644431471824646,
"min": 0.9644431471824646,
"max": 2.8748886585235596,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9197.89453125,
"min": 9197.89453125,
"max": 29473.359375,
"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": 12.903409004211426,
"min": 0.14480222761631012,
"max": 12.94559097290039,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2516.164794921875,
"min": 28.091632843017578,
"max": 2640.900634765625,
"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": 0.06812393334386048,
"min": 0.058494154396826425,
"max": 0.07672596534179962,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2724957333754419,
"min": 0.2339766175873057,
"max": 0.3638472854314993,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.200000847817636,
"min": 0.11192081530473433,
"max": 0.30351523426817917,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.800003391270544,
"min": 0.4476832612189373,
"max": 1.4657117154668358,
"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": 25.568181818181817,
"min": 3.090909090909091,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 136.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.090909090909091,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 136.0,
"max": 1392.0,
"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": "1698267501",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698267878"
},
"total": 377.66375939700004,
"count": 1,
"self": 0.5860419910001156,
"children": {
"run_training.setup": {
"total": 0.03905707300000927,
"count": 1,
"self": 0.03905707300000927
},
"TrainerController.start_learning": {
"total": 377.03866033299994,
"count": 1,
"self": 0.6230955009978061,
"children": {
"TrainerController._reset_env": {
"total": 1.078754430999993,
"count": 1,
"self": 1.078754430999993
},
"TrainerController.advance": {
"total": 375.25084125300214,
"count": 18206,
"self": 0.29057182600161013,
"children": {
"env_step": {
"total": 374.9602694270005,
"count": 18206,
"self": 294.28084995300173,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.3932338769988,
"count": 18206,
"self": 1.2233233700036692,
"children": {
"TorchPolicy.evaluate": {
"total": 79.16991050699514,
"count": 18206,
"self": 79.16991050699514
}
}
},
"workers": {
"total": 0.28618559700001356,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 375.8500335820028,
"count": 18206,
"is_parallel": true,
"self": 160.72587947600402,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0054406439999752365,
"count": 1,
"is_parallel": true,
"self": 0.004379373000006126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010612709999691106,
"count": 10,
"is_parallel": true,
"self": 0.0010612709999691106
}
}
},
"UnityEnvironment.step": {
"total": 0.04297044599999822,
"count": 1,
"is_parallel": true,
"self": 0.00046978099999250844,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003094299999872874,
"count": 1,
"is_parallel": true,
"self": 0.0003094299999872874
},
"communicator.exchange": {
"total": 0.04097108400000593,
"count": 1,
"is_parallel": true,
"self": 0.04097108400000593
},
"steps_from_proto": {
"total": 0.0012201510000124927,
"count": 1,
"is_parallel": true,
"self": 0.00024225100003150146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009778999999809912,
"count": 10,
"is_parallel": true,
"self": 0.0009778999999809912
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.1241541059988,
"count": 18205,
"is_parallel": true,
"self": 8.80845703599394,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.136846088001732,
"count": 18205,
"is_parallel": true,
"self": 5.136846088001732
},
"communicator.exchange": {
"total": 172.5534668029984,
"count": 18205,
"is_parallel": true,
"self": 172.5534668029984
},
"steps_from_proto": {
"total": 28.625384179004726,
"count": 18205,
"is_parallel": true,
"self": 5.541347972997585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.08403620600714,
"count": 182050,
"is_parallel": true,
"self": 23.08403620600714
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013664999994489335,
"count": 1,
"self": 0.00013664999994489335,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 372.6787756480195,
"count": 419034,
"is_parallel": true,
"self": 7.364856809040589,
"children": {
"process_trajectory": {
"total": 212.42998526197894,
"count": 419034,
"is_parallel": true,
"self": 211.87444843197895,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5555368299999941,
"count": 4,
"is_parallel": true,
"self": 0.5555368299999941
}
}
},
"_update_policy": {
"total": 152.883933577,
"count": 90,
"is_parallel": true,
"self": 45.396746824998644,
"children": {
"TorchPPOOptimizer.update": {
"total": 107.48718675200135,
"count": 4587,
"is_parallel": true,
"self": 107.48718675200135
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08583249800005888,
"count": 1,
"self": 0.0007723810000470621,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08506011700001181,
"count": 1,
"self": 0.08506011700001181
}
}
}
}
}
}
}