Youngdal's picture
First Push
c631e10
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.99172043800354,
"min": 0.99172043800354,
"max": 2.8547725677490234,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9458.0380859375,
"min": 9458.0380859375,
"max": 29267.12890625,
"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": 12.691598892211914,
"min": 0.3542790710926056,
"max": 12.691598892211914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2474.86181640625,
"min": 68.73014068603516,
"max": 2564.355224609375,
"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": 0.07154667177968019,
"min": 0.06392932808706903,
"max": 0.07703118029828913,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28618668711872075,
"min": 0.2593400180010255,
"max": 0.3851559014914457,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20744676719985755,
"min": 0.1107517488987879,
"max": 0.2851209140145311,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8297870687994302,
"min": 0.4430069955951516,
"max": 1.3024452766951393,
"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": 25.34090909090909,
"min": 3.0681818181818183,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 135.0,
"max": 1367.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.0681818181818183,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 135.0,
"max": 1367.0,
"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": "1679051507",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679051967"
},
"total": 459.2263032330002,
"count": 1,
"self": 0.43196275500008596,
"children": {
"run_training.setup": {
"total": 0.10501938600009453,
"count": 1,
"self": 0.10501938600009453
},
"TrainerController.start_learning": {
"total": 458.689321092,
"count": 1,
"self": 0.5628872029978993,
"children": {
"TrainerController._reset_env": {
"total": 9.330650070000047,
"count": 1,
"self": 9.330650070000047
},
"TrainerController.advance": {
"total": 448.66054164500224,
"count": 18201,
"self": 0.27057816400520096,
"children": {
"env_step": {
"total": 448.38996348099704,
"count": 18201,
"self": 324.9861573639946,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.13320221599565,
"count": 18201,
"self": 1.9392239839971808,
"children": {
"TorchPolicy.evaluate": {
"total": 121.19397823199847,
"count": 18201,
"self": 121.19397823199847
}
}
},
"workers": {
"total": 0.2706039010067798,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.2987147289798,
"count": 18201,
"is_parallel": true,
"self": 220.08427475099393,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005190869999978531,
"count": 1,
"is_parallel": true,
"self": 0.003642050999815183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015488190001633484,
"count": 10,
"is_parallel": true,
"self": 0.0015488190001633484
}
}
},
"UnityEnvironment.step": {
"total": 0.03895242200019311,
"count": 1,
"is_parallel": true,
"self": 0.0005238780001945997,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002538230000936892,
"count": 1,
"is_parallel": true,
"self": 0.0002538230000936892
},
"communicator.exchange": {
"total": 0.03641483999990669,
"count": 1,
"is_parallel": true,
"self": 0.03641483999990669
},
"steps_from_proto": {
"total": 0.0017598809999981313,
"count": 1,
"is_parallel": true,
"self": 0.0003678190003029158,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013920619996952155,
"count": 10,
"is_parallel": true,
"self": 0.0013920619996952155
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.21443997798588,
"count": 18200,
"is_parallel": true,
"self": 9.199032889992168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.0497423649928805,
"count": 18200,
"is_parallel": true,
"self": 5.0497423649928805
},
"communicator.exchange": {
"total": 192.79715061399997,
"count": 18200,
"is_parallel": true,
"self": 192.79715061399997
},
"steps_from_proto": {
"total": 30.168514109000853,
"count": 18200,
"is_parallel": true,
"self": 5.920627190989535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.247886918011318,
"count": 182000,
"is_parallel": true,
"self": 24.247886918011318
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012362600000415114,
"count": 1,
"self": 0.00012362600000415114,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.5814107579831,
"count": 381845,
"is_parallel": true,
"self": 9.5979554069595,
"children": {
"process_trajectory": {
"total": 244.7203536680238,
"count": 381845,
"is_parallel": true,
"self": 243.0506716570237,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6696820110000772,
"count": 4,
"is_parallel": true,
"self": 1.6696820110000772
}
}
},
"_update_policy": {
"total": 191.26310168299983,
"count": 90,
"is_parallel": true,
"self": 74.64727293799479,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.61582874500505,
"count": 4584,
"is_parallel": true,
"self": 116.61582874500505
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13511854799980938,
"count": 1,
"self": 0.0009335349998309539,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13418501299997843,
"count": 1,
"self": 0.13418501299997843
}
}
}
}
}
}
}