duwi's picture
First Push
7b2cfa8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8680651187896729,
"min": 0.8543922901153564,
"max": 2.8583240509033203,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8345.578125,
"min": 8345.578125,
"max": 29334.978515625,
"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": 12.67759895324707,
"min": 0.31291666626930237,
"max": 12.67759895324707,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2472.1318359375,
"min": 60.705833435058594,
"max": 2553.53515625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.363636363636363,
"min": 3.1136363636363638,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 137.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.1136363636363638,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 137.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06800169031196798,
"min": 0.061406312064968466,
"max": 0.07431160807141615,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27200676124787193,
"min": 0.24562524825987386,
"max": 0.3589785393029588,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2021523997479794,
"min": 0.11591664270392857,
"max": 0.2730652761517786,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8086095989919176,
"min": 0.4636665708157143,
"max": 1.3273262644515318,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029184900271699997,
"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": 0.19728300000000004,
"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": 0.0048644217,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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": "1696517632",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1696518257"
},
"total": 624.9292311900001,
"count": 1,
"self": 1.1204338440001038,
"children": {
"run_training.setup": {
"total": 0.0613411009999254,
"count": 1,
"self": 0.0613411009999254
},
"TrainerController.start_learning": {
"total": 623.7474562450001,
"count": 1,
"self": 0.8917004820020793,
"children": {
"TrainerController._reset_env": {
"total": 1.5867170740000347,
"count": 1,
"self": 1.5867170740000347
},
"TrainerController.advance": {
"total": 620.9860222169979,
"count": 18225,
"self": 0.44205455298526886,
"children": {
"env_step": {
"total": 620.5439676640126,
"count": 18225,
"self": 501.46504454203273,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.64437984598487,
"count": 18225,
"self": 2.831956582988937,
"children": {
"TorchPolicy.evaluate": {
"total": 115.81242326299594,
"count": 18225,
"self": 115.81242326299594
}
}
},
"workers": {
"total": 0.4345432759949972,
"count": 18225,
"self": 0.0,
"children": {
"worker_root": {
"total": 621.1954206030114,
"count": 18225,
"is_parallel": true,
"self": 272.07395110602783,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007583498000030886,
"count": 1,
"is_parallel": true,
"self": 0.005438765000121748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002144732999909138,
"count": 10,
"is_parallel": true,
"self": 0.002144732999909138
}
}
},
"UnityEnvironment.step": {
"total": 0.05042009900000721,
"count": 1,
"is_parallel": true,
"self": 0.0007986750000554821,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006021079999527501,
"count": 1,
"is_parallel": true,
"self": 0.0006021079999527501
},
"communicator.exchange": {
"total": 0.043922598999984075,
"count": 1,
"is_parallel": true,
"self": 0.043922598999984075
},
"steps_from_proto": {
"total": 0.005096717000014905,
"count": 1,
"is_parallel": true,
"self": 0.0014488979998077411,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003647819000207164,
"count": 10,
"is_parallel": true,
"self": 0.003647819000207164
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 349.12146949698354,
"count": 18224,
"is_parallel": true,
"self": 15.353987829986409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.139155371011725,
"count": 18224,
"is_parallel": true,
"self": 8.139155371011725
},
"communicator.exchange": {
"total": 275.64216610699816,
"count": 18224,
"is_parallel": true,
"self": 275.64216610699816
},
"steps_from_proto": {
"total": 49.98616018898724,
"count": 18224,
"is_parallel": true,
"self": 9.80662720301359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.17953298597365,
"count": 182240,
"is_parallel": true,
"self": 40.17953298597365
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021263899998302804,
"count": 1,
"self": 0.00021263899998302804,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 615.2367136440141,
"count": 622825,
"is_parallel": true,
"self": 15.625087626101276,
"children": {
"process_trajectory": {
"total": 329.4909477069125,
"count": 622825,
"is_parallel": true,
"self": 327.50656520991254,
"children": {
"RLTrainer._checkpoint": {
"total": 1.984382496999956,
"count": 4,
"is_parallel": true,
"self": 1.984382496999956
}
}
},
"_update_policy": {
"total": 270.12067831100035,
"count": 90,
"is_parallel": true,
"self": 97.72558729600473,
"children": {
"TorchPPOOptimizer.update": {
"total": 172.39509101499561,
"count": 4587,
"is_parallel": true,
"self": 172.39509101499561
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.28280383300011636,
"count": 1,
"self": 0.0027724199999283883,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28003141300018797,
"count": 1,
"self": 0.28003141300018797
}
}
}
}
}
}
}