iammartian0's picture
First Push
a5b3661
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.039778470993042,
"min": 1.039778470993042,
"max": 2.862570285797119,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9927.8046875,
"min": 9927.8046875,
"max": 29315.58203125,
"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": 12.681059837341309,
"min": 0.2109851837158203,
"max": 12.681059837341309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2472.806640625,
"min": 40.93112564086914,
"max": 2574.9931640625,
"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": 0.06917356912191619,
"min": 0.06016283334868015,
"max": 0.07442419768952224,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27669427648766476,
"min": 0.2406513333947206,
"max": 0.36021762152028947,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20765924585216183,
"min": 0.09565932270910993,
"max": 0.269076180370415,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8306369834086473,
"min": 0.3826372908364397,
"max": 1.3261109085059632,
"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": 24.727272727272727,
"min": 3.0681818181818183,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1088.0,
"min": 135.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.727272727272727,
"min": 3.0681818181818183,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1088.0,
"min": 135.0,
"max": 1375.0,
"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": "1676030338",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676030832"
},
"total": 493.9526420169999,
"count": 1,
"self": 0.4372699410000678,
"children": {
"run_training.setup": {
"total": 0.11904346999995141,
"count": 1,
"self": 0.11904346999995141
},
"TrainerController.start_learning": {
"total": 493.3963286059999,
"count": 1,
"self": 0.5407699709901408,
"children": {
"TrainerController._reset_env": {
"total": 8.974428231000047,
"count": 1,
"self": 8.974428231000047
},
"TrainerController.advance": {
"total": 483.7544669090099,
"count": 18200,
"self": 0.28842800999723295,
"children": {
"env_step": {
"total": 483.4660388990127,
"count": 18200,
"self": 337.60440782199987,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.58354680400203,
"count": 18200,
"self": 1.5814699969997719,
"children": {
"TorchPolicy.evaluate": {
"total": 144.00207680700225,
"count": 18200,
"self": 32.60849922099578,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.39357758600647,
"count": 18200,
"self": 111.39357758600647
}
}
}
}
},
"workers": {
"total": 0.27808427301079064,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.6322487209994,
"count": 18200,
"is_parallel": true,
"self": 239.11055169900646,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006337423999980274,
"count": 1,
"is_parallel": true,
"self": 0.003727839999896787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002609584000083487,
"count": 10,
"is_parallel": true,
"self": 0.002609584000083487
}
}
},
"UnityEnvironment.step": {
"total": 0.07442076699999234,
"count": 1,
"is_parallel": true,
"self": 0.0005523620001213203,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045954799998071394,
"count": 1,
"is_parallel": true,
"self": 0.00045954799998071394
},
"communicator.exchange": {
"total": 0.07130353699994885,
"count": 1,
"is_parallel": true,
"self": 0.07130353699994885
},
"steps_from_proto": {
"total": 0.0021053199999414574,
"count": 1,
"is_parallel": true,
"self": 0.000471739999966303,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016335799999751544,
"count": 10,
"is_parallel": true,
"self": 0.0016335799999751544
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.52169702199296,
"count": 18199,
"is_parallel": true,
"self": 9.996799714992903,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.43572769800835,
"count": 18199,
"is_parallel": true,
"self": 5.43572769800835
},
"communicator.exchange": {
"total": 203.06721936499912,
"count": 18199,
"is_parallel": true,
"self": 203.06721936499912
},
"steps_from_proto": {
"total": 34.02195024399259,
"count": 18199,
"is_parallel": true,
"self": 7.39515106298677,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.626799181005822,
"count": 181990,
"is_parallel": true,
"self": 26.626799181005822
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017488899993622908,
"count": 1,
"self": 0.00017488899993622908,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 479.9407039820305,
"count": 435768,
"is_parallel": true,
"self": 11.462421674109464,
"children": {
"process_trajectory": {
"total": 273.90539661392097,
"count": 435768,
"is_parallel": true,
"self": 272.6935054869209,
"children": {
"RLTrainer._checkpoint": {
"total": 1.211891127000058,
"count": 4,
"is_parallel": true,
"self": 1.211891127000058
}
}
},
"_update_policy": {
"total": 194.5728856940001,
"count": 90,
"is_parallel": true,
"self": 74.10001251500762,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.47287317899247,
"count": 4587,
"is_parallel": true,
"self": 120.47287317899247
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1264886059998389,
"count": 1,
"self": 0.0009327229997779796,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12555588300006093,
"count": 1,
"self": 0.12555588300006093
}
}
}
}
}
}
}