afos950's picture
First Push
90a4ae1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8969330787658691,
"min": 0.8969330787658691,
"max": 2.8592638969421387,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8573.783203125,
"min": 8573.783203125,
"max": 29281.720703125,
"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": 13.082232475280762,
"min": 0.39711835980415344,
"max": 13.082232475280762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2551.035400390625,
"min": 77.04096221923828,
"max": 2657.828125,
"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": 0.07018812911701389,
"min": 0.06285471567493468,
"max": 0.07534257062373703,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28075251646805555,
"min": 0.258982749555406,
"max": 0.3710925873305065,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.208245359945531,
"min": 0.12157158738495234,
"max": 0.2859097709842757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.832981439782124,
"min": 0.48628634953980937,
"max": 1.4295488549213786,
"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": 25.704545454545453,
"min": 3.3636363636363638,
"max": 25.945454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 148.0,
"max": 1427.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.3636363636363638,
"max": 25.945454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 148.0,
"max": 1427.0,
"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": "1684330537",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1684331191"
},
"total": 654.2486017089999,
"count": 1,
"self": 0.5853276000000278,
"children": {
"run_training.setup": {
"total": 0.05706266299989693,
"count": 1,
"self": 0.05706266299989693
},
"TrainerController.start_learning": {
"total": 653.606211446,
"count": 1,
"self": 0.9906029990104344,
"children": {
"TrainerController._reset_env": {
"total": 0.9611052490000702,
"count": 1,
"self": 0.9611052490000702
},
"TrainerController.advance": {
"total": 651.4928223169893,
"count": 18202,
"self": 0.4790314559812714,
"children": {
"env_step": {
"total": 651.013790861008,
"count": 18202,
"self": 528.2970410320207,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.24840860699953,
"count": 18202,
"self": 3.2516334570137815,
"children": {
"TorchPolicy.evaluate": {
"total": 118.99677514998575,
"count": 18202,
"self": 118.99677514998575
}
}
},
"workers": {
"total": 0.46834122198777095,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 650.8683578060112,
"count": 18202,
"is_parallel": true,
"self": 279.0115798290062,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0070814800000107425,
"count": 1,
"is_parallel": true,
"self": 0.005197711000050731,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018837689999600116,
"count": 10,
"is_parallel": true,
"self": 0.0018837689999600116
}
}
},
"UnityEnvironment.step": {
"total": 0.049395741000012094,
"count": 1,
"is_parallel": true,
"self": 0.0008290160000115065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045231399997192057,
"count": 1,
"is_parallel": true,
"self": 0.00045231399997192057
},
"communicator.exchange": {
"total": 0.045466270000019904,
"count": 1,
"is_parallel": true,
"self": 0.045466270000019904
},
"steps_from_proto": {
"total": 0.0026481410000087635,
"count": 1,
"is_parallel": true,
"self": 0.0004786729999750605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002169468000033703,
"count": 10,
"is_parallel": true,
"self": 0.002169468000033703
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 371.856777977005,
"count": 18201,
"is_parallel": true,
"self": 15.42603389101805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.401311024009715,
"count": 18201,
"is_parallel": true,
"self": 8.401311024009715
},
"communicator.exchange": {
"total": 298.09849496198797,
"count": 18201,
"is_parallel": true,
"self": 298.09849496198797
},
"steps_from_proto": {
"total": 49.93093809998925,
"count": 18201,
"is_parallel": true,
"self": 10.19034622599088,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.74059187399837,
"count": 182010,
"is_parallel": true,
"self": 39.74059187399837
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.002392428000121072,
"count": 1,
"self": 0.002392428000121072,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 645.526197043019,
"count": 695547,
"is_parallel": true,
"self": 16.266877240974736,
"children": {
"process_trajectory": {
"total": 351.47132392904405,
"count": 695547,
"is_parallel": true,
"self": 349.484528136044,
"children": {
"RLTrainer._checkpoint": {
"total": 1.9867957930000557,
"count": 4,
"is_parallel": true,
"self": 1.9867957930000557
}
}
},
"_update_policy": {
"total": 277.7879958730002,
"count": 90,
"is_parallel": true,
"self": 99.57340855200368,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.21458732099654,
"count": 4587,
"is_parallel": true,
"self": 178.21458732099654
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15928845300004468,
"count": 1,
"self": 0.0012420680000104767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1580463850000342,
"count": 1,
"self": 0.1580463850000342
}
}
}
}
}
}
}