scronberg's picture
First training
962cbc8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9950824975967407,
"min": 0.9950824975967407,
"max": 2.8652212619781494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9501.0478515625,
"min": 9501.0478515625,
"max": 29342.73046875,
"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": 12.98351001739502,
"min": 0.3952019214630127,
"max": 12.98351001739502,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.784423828125,
"min": 76.66917419433594,
"max": 2614.113525390625,
"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": 0.07024703434909302,
"min": 0.06096724096278194,
"max": 0.07922441743921452,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2809881373963721,
"min": 0.24386896385112777,
"max": 0.3480193871849527,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2063585081886427,
"min": 0.13131834407720494,
"max": 0.28407682349868846,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8254340327545708,
"min": 0.5252733763088198,
"max": 1.4203841174934424,
"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": 25.568181818181817,
"min": 3.5,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 154.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.5,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 154.0,
"max": 1397.0,
"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": "1673870326",
"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": "1673870772"
},
"total": 446.1458944799999,
"count": 1,
"self": 0.39063136499993334,
"children": {
"run_training.setup": {
"total": 0.11732637799997292,
"count": 1,
"self": 0.11732637799997292
},
"TrainerController.start_learning": {
"total": 445.637936737,
"count": 1,
"self": 0.5441666000009491,
"children": {
"TrainerController._reset_env": {
"total": 11.14278250999999,
"count": 1,
"self": 11.14278250999999
},
"TrainerController.advance": {
"total": 433.8278615029991,
"count": 18200,
"self": 0.2870861979964161,
"children": {
"env_step": {
"total": 433.5407753050027,
"count": 18200,
"self": 283.8534304720059,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.40220304399423,
"count": 18200,
"self": 1.409015090993222,
"children": {
"TorchPolicy.evaluate": {
"total": 147.993187953001,
"count": 18200,
"self": 33.050068081002024,
"children": {
"TorchPolicy.sample_actions": {
"total": 114.94311987199899,
"count": 18200,
"self": 114.94311987199899
}
}
}
}
},
"workers": {
"total": 0.28514178900249476,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.4273808710064,
"count": 18200,
"is_parallel": true,
"self": 216.1549571160125,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005482212999993408,
"count": 1,
"is_parallel": true,
"self": 0.003094354000012345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002387858999981063,
"count": 10,
"is_parallel": true,
"self": 0.002387858999981063
}
}
},
"UnityEnvironment.step": {
"total": 0.10300313699997332,
"count": 1,
"is_parallel": true,
"self": 0.000514347999938991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003341660000160118,
"count": 1,
"is_parallel": true,
"self": 0.0003341660000160118
},
"communicator.exchange": {
"total": 0.10037658699999952,
"count": 1,
"is_parallel": true,
"self": 0.10037658699999952
},
"steps_from_proto": {
"total": 0.0017780360000188011,
"count": 1,
"is_parallel": true,
"self": 0.0003890490000060254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013889870000127758,
"count": 10,
"is_parallel": true,
"self": 0.0013889870000127758
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.2724237549939,
"count": 18199,
"is_parallel": true,
"self": 8.701164216999047,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.149936831994381,
"count": 18199,
"is_parallel": true,
"self": 5.149936831994381
},
"communicator.exchange": {
"total": 183.11497891299825,
"count": 18199,
"is_parallel": true,
"self": 183.11497891299825
},
"steps_from_proto": {
"total": 31.306343793002213,
"count": 18199,
"is_parallel": true,
"self": 6.768700531991527,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.537643261010686,
"count": 181990,
"is_parallel": true,
"self": 24.537643261010686
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.844399998342851e-05,
"count": 1,
"self": 3.844399998342851e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 430.76707230799184,
"count": 352690,
"is_parallel": true,
"self": 9.421221153995987,
"children": {
"process_trajectory": {
"total": 245.2745162089959,
"count": 352690,
"is_parallel": true,
"self": 244.55527515699603,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7192410519998589,
"count": 4,
"is_parallel": true,
"self": 0.7192410519998589
}
}
},
"_update_policy": {
"total": 176.07133494499996,
"count": 90,
"is_parallel": true,
"self": 46.064766627001575,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.0065683179984,
"count": 4587,
"is_parallel": true,
"self": 130.0065683179984
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12308768000002601,
"count": 1,
"self": 0.0009681910000836069,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1221194889999424,
"count": 1,
"self": 0.1221194889999424
}
}
}
}
}
}
}