zyoscovits's picture
First push to repo
150cacf
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6779228448867798,
"min": 0.6779228448867798,
"max": 2.8712780475616455,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6472.80712890625,
"min": 6472.80712890625,
"max": 29404.7578125,
"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": 12.87601375579834,
"min": 0.3963603377342224,
"max": 12.902161598205566,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.82275390625,
"min": 76.89390563964844,
"max": 2632.041015625,
"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": 0.06444238151715243,
"min": 0.06372641238724064,
"max": 0.07627596412039209,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2577695260686097,
"min": 0.2577695260686097,
"max": 0.37104290902988946,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1940157530719743,
"min": 0.12757494187612525,
"max": 0.29046313920441796,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7760630122878972,
"min": 0.510299767504501,
"max": 1.4523156960220898,
"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": 24.977272727272727,
"min": 3.522727272727273,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1099.0,
"min": 155.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.977272727272727,
"min": 3.522727272727273,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1099.0,
"min": 155.0,
"max": 1404.0,
"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": "1673816432",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673816847"
},
"total": 415.4082729810001,
"count": 1,
"self": 0.38874081000005845,
"children": {
"run_training.setup": {
"total": 0.11755722700002025,
"count": 1,
"self": 0.11755722700002025
},
"TrainerController.start_learning": {
"total": 414.901974944,
"count": 1,
"self": 0.5127563270100381,
"children": {
"TrainerController._reset_env": {
"total": 9.622878540999977,
"count": 1,
"self": 9.622878540999977
},
"TrainerController.advance": {
"total": 404.65315021698984,
"count": 18201,
"self": 0.24903188397661324,
"children": {
"env_step": {
"total": 404.40411833301323,
"count": 18201,
"self": 264.12555284601956,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.02503921000095,
"count": 18201,
"self": 1.312274844001422,
"children": {
"TorchPolicy.evaluate": {
"total": 138.71276436599953,
"count": 18201,
"self": 30.54805735798891,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.16470700801062,
"count": 18201,
"self": 108.16470700801062
}
}
}
}
},
"workers": {
"total": 0.2535262769927158,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.76660316998573,
"count": 18201,
"is_parallel": true,
"self": 202.94936499896608,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.012217057000043496,
"count": 1,
"is_parallel": true,
"self": 0.009524199999987104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026928570000563923,
"count": 10,
"is_parallel": true,
"self": 0.0026928570000563923
}
}
},
"UnityEnvironment.step": {
"total": 0.031852645999947526,
"count": 1,
"is_parallel": true,
"self": 0.0005219299999907889,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002756909999561685,
"count": 1,
"is_parallel": true,
"self": 0.0002756909999561685
},
"communicator.exchange": {
"total": 0.029244310000080986,
"count": 1,
"is_parallel": true,
"self": 0.029244310000080986
},
"steps_from_proto": {
"total": 0.0018107149999195826,
"count": 1,
"is_parallel": true,
"self": 0.0004141500002106113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013965649997089713,
"count": 10,
"is_parallel": true,
"self": 0.0013965649997089713
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.81723817101965,
"count": 18200,
"is_parallel": true,
"self": 8.147783086005234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.842574879017434,
"count": 18200,
"is_parallel": true,
"self": 4.842574879017434
},
"communicator.exchange": {
"total": 168.5209294970049,
"count": 18200,
"is_parallel": true,
"self": 168.5209294970049
},
"steps_from_proto": {
"total": 29.3059507089921,
"count": 18200,
"is_parallel": true,
"self": 6.155248286996766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.150702421995334,
"count": 182000,
"is_parallel": true,
"self": 23.150702421995334
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.146999999145919e-05,
"count": 1,
"self": 6.146999999145919e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 402.0441324049292,
"count": 322722,
"is_parallel": true,
"self": 8.35653213892681,
"children": {
"process_trajectory": {
"total": 229.4016362820023,
"count": 322722,
"is_parallel": true,
"self": 228.70656664200214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6950696400001561,
"count": 4,
"is_parallel": true,
"self": 0.6950696400001561
}
}
},
"_update_policy": {
"total": 164.2859639840001,
"count": 90,
"is_parallel": true,
"self": 43.746694770003046,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.53926921399704,
"count": 4587,
"is_parallel": true,
"self": 120.53926921399704
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11312838900016686,
"count": 1,
"self": 0.0007919750000837666,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1123364140000831,
"count": 1,
"self": 0.1123364140000831
}
}
}
}
}
}
}