phonenix's picture
First Push
d0bc9b0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9109290838241577,
"min": 0.9041577577590942,
"max": 2.8688838481903076,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8697.55078125,
"min": 8697.55078125,
"max": 29380.23828125,
"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": 12.99654483795166,
"min": 0.4710986316204071,
"max": 12.99654483795166,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.326171875,
"min": 91.39313507080078,
"max": 2658.99951171875,
"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": 0.07552775284406665,
"min": 0.0622904996184219,
"max": 0.07552775284406665,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3021110113762666,
"min": 0.2491619984736876,
"max": 0.37554828525297157,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2179013716385645,
"min": 0.1179013895806765,
"max": 0.2919317928015017,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.871605486554258,
"min": 0.471605558322706,
"max": 1.4154356907980115,
"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": 25.295454545454547,
"min": 3.340909090909091,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 147.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.340909090909091,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 147.0,
"max": 1414.0,
"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": "1676478053",
"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": "1676478494"
},
"total": 440.83965807900006,
"count": 1,
"self": 0.3891303579999885,
"children": {
"run_training.setup": {
"total": 0.18933207800000673,
"count": 1,
"self": 0.18933207800000673
},
"TrainerController.start_learning": {
"total": 440.26119564300006,
"count": 1,
"self": 0.4811961889977283,
"children": {
"TrainerController._reset_env": {
"total": 9.414689142999976,
"count": 1,
"self": 9.414689142999976
},
"TrainerController.advance": {
"total": 430.2461628990024,
"count": 18201,
"self": 0.2635408850001113,
"children": {
"env_step": {
"total": 429.9826220140023,
"count": 18201,
"self": 293.71700207999834,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.00946886800358,
"count": 18201,
"self": 1.4005611909975073,
"children": {
"TorchPolicy.evaluate": {
"total": 134.60890767700607,
"count": 18201,
"self": 29.698548460006805,
"children": {
"TorchPolicy.sample_actions": {
"total": 104.91035921699927,
"count": 18201,
"self": 104.91035921699927
}
}
}
}
},
"workers": {
"total": 0.2561510660003705,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.96168097199404,
"count": 18201,
"is_parallel": true,
"self": 214.9147553549887,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00558986100003267,
"count": 1,
"is_parallel": true,
"self": 0.00281993099997635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00276993000005632,
"count": 10,
"is_parallel": true,
"self": 0.00276993000005632
}
}
},
"UnityEnvironment.step": {
"total": 0.034123675999978786,
"count": 1,
"is_parallel": true,
"self": 0.0005573010000148315,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035127699999293327,
"count": 1,
"is_parallel": true,
"self": 0.00035127699999293327
},
"communicator.exchange": {
"total": 0.0312086929999964,
"count": 1,
"is_parallel": true,
"self": 0.0312086929999964
},
"steps_from_proto": {
"total": 0.0020064049999746203,
"count": 1,
"is_parallel": true,
"self": 0.000427282999964973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015791220000096473,
"count": 10,
"is_parallel": true,
"self": 0.0015791220000096473
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.04692561700534,
"count": 18200,
"is_parallel": true,
"self": 9.236591035998629,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.0134550700058185,
"count": 18200,
"is_parallel": true,
"self": 5.0134550700058185
},
"communicator.exchange": {
"total": 179.89221991100322,
"count": 18200,
"is_parallel": true,
"self": 179.89221991100322
},
"steps_from_proto": {
"total": 29.90465959999767,
"count": 18200,
"is_parallel": true,
"self": 6.434513381991849,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.470146218005823,
"count": 182000,
"is_parallel": true,
"self": 23.470146218005823
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010217099998044432,
"count": 1,
"self": 0.00010217099998044432,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 427.0043804109892,
"count": 390386,
"is_parallel": true,
"self": 9.650419791025001,
"children": {
"process_trajectory": {
"total": 245.86525320396413,
"count": 390386,
"is_parallel": true,
"self": 245.20596837996408,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6592848240000535,
"count": 4,
"is_parallel": true,
"self": 0.6592848240000535
}
}
},
"_update_policy": {
"total": 171.48870741600007,
"count": 90,
"is_parallel": true,
"self": 58.597872741999026,
"children": {
"TorchPPOOptimizer.update": {
"total": 112.89083467400104,
"count": 4587,
"is_parallel": true,
"self": 112.89083467400104
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1190452409999807,
"count": 1,
"self": 0.0008543789999748697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11819086200000584,
"count": 1,
"self": 0.11819086200000584
}
}
}
}
}
}
}