rrozb's picture
First Push
38bdcf2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0284528732299805,
"min": 1.0284528732299805,
"max": 2.862475872039795,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9853.607421875,
"min": 9853.607421875,
"max": 29346.103515625,
"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": 12.660928726196289,
"min": 0.4049602448940277,
"max": 12.69804573059082,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.881103515625,
"min": 78.56228637695312,
"max": 2590.4013671875,
"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": 0.07556634124639638,
"min": 0.06271791901695085,
"max": 0.07895789275957499,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30226536498558554,
"min": 0.25635228294051526,
"max": 0.39478946379787494,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19126306393859432,
"min": 0.14646041134427135,
"max": 0.30141675990878364,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7650522557543773,
"min": 0.5858416453770854,
"max": 1.2105530848105748,
"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": 24.704545454545453,
"min": 4.113636363636363,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1087.0,
"min": 181.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.704545454545453,
"min": 4.113636363636363,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1087.0,
"min": 181.0,
"max": 1389.0,
"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": "1693715083",
"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": "1693715541"
},
"total": 457.49418166600003,
"count": 1,
"self": 0.7784750189999841,
"children": {
"run_training.setup": {
"total": 0.06208332599999267,
"count": 1,
"self": 0.06208332599999267
},
"TrainerController.start_learning": {
"total": 456.65362332100005,
"count": 1,
"self": 0.5622178320028297,
"children": {
"TrainerController._reset_env": {
"total": 5.601381286999981,
"count": 1,
"self": 5.601381286999981
},
"TrainerController.advance": {
"total": 450.2725550279972,
"count": 18222,
"self": 0.2601363889932031,
"children": {
"env_step": {
"total": 450.012418639004,
"count": 18222,
"self": 326.9397590000103,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.80809547399329,
"count": 18222,
"self": 1.6353023889994631,
"children": {
"TorchPolicy.evaluate": {
"total": 121.17279308499383,
"count": 18222,
"self": 121.17279308499383
}
}
},
"workers": {
"total": 0.26456416500042224,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.13213539199734,
"count": 18222,
"is_parallel": true,
"self": 215.64315075800687,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006682759999989685,
"count": 1,
"is_parallel": true,
"self": 0.0045132779999903505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021694819999993342,
"count": 10,
"is_parallel": true,
"self": 0.0021694819999993342
}
}
},
"UnityEnvironment.step": {
"total": 0.04799680600001466,
"count": 1,
"is_parallel": true,
"self": 0.0005929950000052031,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003163629999960449,
"count": 1,
"is_parallel": true,
"self": 0.0003163629999960449
},
"communicator.exchange": {
"total": 0.044990247000015415,
"count": 1,
"is_parallel": true,
"self": 0.044990247000015415
},
"steps_from_proto": {
"total": 0.0020972009999979946,
"count": 1,
"is_parallel": true,
"self": 0.00048132199992778624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016158790000702083,
"count": 10,
"is_parallel": true,
"self": 0.0016158790000702083
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.48898463399047,
"count": 18221,
"is_parallel": true,
"self": 10.125662128994861,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.186288983995979,
"count": 18221,
"is_parallel": true,
"self": 5.186288983995979
},
"communicator.exchange": {
"total": 189.73214463400075,
"count": 18221,
"is_parallel": true,
"self": 189.73214463400075
},
"steps_from_proto": {
"total": 34.44488888699888,
"count": 18221,
"is_parallel": true,
"self": 6.183180329985248,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.261708557013634,
"count": 182210,
"is_parallel": true,
"self": 28.261708557013634
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014345400006732234,
"count": 1,
"self": 0.00014345400006732234,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.9232106750477,
"count": 414388,
"is_parallel": true,
"self": 8.990518183072481,
"children": {
"process_trajectory": {
"total": 243.91195572897544,
"count": 414388,
"is_parallel": true,
"self": 242.66654490897548,
"children": {
"RLTrainer._checkpoint": {
"total": 1.245410819999961,
"count": 4,
"is_parallel": true,
"self": 1.245410819999961
}
}
},
"_update_policy": {
"total": 194.02073676299977,
"count": 90,
"is_parallel": true,
"self": 75.62464105099605,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.39609571200373,
"count": 4587,
"is_parallel": true,
"self": 118.39609571200373
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21732571999996253,
"count": 1,
"self": 0.001126897999938592,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21619882200002394,
"count": 1,
"self": 0.21619882200002394
}
}
}
}
}
}
}