Schadom's picture
First Push
02da5ff
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.671863853931427,
"min": 0.6356419324874878,
"max": 2.877934455871582,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 2985.762939453125,
"min": 2875.107177734375,
"max": 15258.80859375,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 4976.0,
"max": 499976.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 4976.0,
"max": 499976.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.756805181503296,
"min": 0.08927416801452637,
"max": 2.852208375930786,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 270.1669006347656,
"min": 8.659594535827637,
"max": 301.35858154296875,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06379264582966582,
"min": 0.057747382852539886,
"max": 0.07960642214782317,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.12758529165933163,
"min": 0.11549476570507977,
"max": 0.226370559068278,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.10603109907870199,
"min": 0.06946047927782524,
"max": 0.1824750304952556,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.21206219815740399,
"min": 0.13892095855565048,
"max": 0.4828019254640037,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.7880996424000114e-06,
"min": 1.7880996424000114e-06,
"max": 0.0004967880006423999,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5761992848000227e-06,
"min": 3.5761992848000227e-06,
"max": 0.0014474640105071998,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10035760000000002,
"min": 0.10035760000000002,
"max": 0.19935760000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20071520000000004,
"min": 0.20071520000000004,
"max": 0.5894928000000002,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.784424000000012e-05,
"min": 2.784424000000012e-05,
"max": 0.00496794424,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 5.568848000000024e-05,
"min": 5.568848000000024e-05,
"max": 0.014475690719999998,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.956521739130434,
"min": 3.3636363636363638,
"max": 28.181818181818183,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 620.0,
"min": 74.0,
"max": 909.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.956521739130434,
"min": 3.3636363636363638,
"max": 28.181818181818183,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 620.0,
"min": 74.0,
"max": 909.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1699539140",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget6 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699540283"
},
"total": 1143.060384849,
"count": 1,
"self": 0.43120760900001187,
"children": {
"run_training.setup": {
"total": 0.04388156400000298,
"count": 1,
"self": 0.04388156400000298
},
"TrainerController.start_learning": {
"total": 1142.585295676,
"count": 1,
"self": 1.3304583110093517,
"children": {
"TrainerController._reset_env": {
"total": 4.007827991999875,
"count": 1,
"self": 4.007827991999875
},
"TrainerController.advance": {
"total": 1137.1285564769905,
"count": 45474,
"self": 0.6853195342509935,
"children": {
"env_step": {
"total": 1136.4432369427395,
"count": 45474,
"self": 779.2986235999397,
"children": {
"SubprocessEnvManager._take_step": {
"total": 356.45992052885595,
"count": 45474,
"self": 3.4593523239518618,
"children": {
"TorchPolicy.evaluate": {
"total": 353.0005682049041,
"count": 45474,
"self": 353.0005682049041
}
}
},
"workers": {
"total": 0.6846928139439115,
"count": 45474,
"self": 0.0,
"children": {
"worker_root": {
"total": 1139.4967643440004,
"count": 45474,
"is_parallel": true,
"self": 546.8811227458373,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020197270005155588,
"count": 1,
"is_parallel": true,
"self": 0.0006211160007296712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013986109997858875,
"count": 10,
"is_parallel": true,
"self": 0.0013986109997858875
}
}
},
"UnityEnvironment.step": {
"total": 0.05148786600057065,
"count": 1,
"is_parallel": true,
"self": 0.0006415170009859139,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027017499996873084,
"count": 1,
"is_parallel": true,
"self": 0.00027017499996873084
},
"communicator.exchange": {
"total": 0.04878064900003665,
"count": 1,
"is_parallel": true,
"self": 0.04878064900003665
},
"steps_from_proto": {
"total": 0.0017955249995793565,
"count": 1,
"is_parallel": true,
"self": 0.00035710599968297174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014384189998963848,
"count": 10,
"is_parallel": true,
"self": 0.0014384189998963848
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 592.6156415981632,
"count": 45473,
"is_parallel": true,
"self": 26.362666569263638,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.688147001960715,
"count": 45473,
"is_parallel": true,
"self": 13.688147001960715
},
"communicator.exchange": {
"total": 466.68495769804576,
"count": 45473,
"is_parallel": true,
"self": 466.68495769804576
},
"steps_from_proto": {
"total": 85.87987032889305,
"count": 45473,
"is_parallel": true,
"self": 16.165522159294596,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.71434816959845,
"count": 454730,
"is_parallel": true,
"self": 69.71434816959845
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012229799995111534,
"count": 1,
"self": 0.00012229799995111534,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1127.6624542446043,
"count": 1134204,
"is_parallel": true,
"self": 25.01804809985515,
"children": {
"process_trajectory": {
"total": 634.9563549717523,
"count": 1134204,
"is_parallel": true,
"self": 632.8101903627539,
"children": {
"RLTrainer._checkpoint": {
"total": 2.1461646089983333,
"count": 10,
"is_parallel": true,
"self": 2.1461646089983333
}
}
},
"_update_policy": {
"total": 467.6880511729969,
"count": 227,
"is_parallel": true,
"self": 140.43815976804672,
"children": {
"TorchPPOOptimizer.update": {
"total": 327.2498914049502,
"count": 11574,
"is_parallel": true,
"self": 327.2498914049502
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11833059800028423,
"count": 1,
"self": 0.0017238740001630504,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11660672400012118,
"count": 1,
"self": 0.11660672400012118
}
}
}
}
}
}
}