haanjack's picture
First Push
cb94fb4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0170955657958984,
"min": 1.0170955657958984,
"max": 2.8678665161132812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9711.228515625,
"min": 9711.228515625,
"max": 29369.8203125,
"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": 12.28547191619873,
"min": 0.3764294981956482,
"max": 12.28547191619873,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2395.6669921875,
"min": 73.0273208618164,
"max": 2487.25830078125,
"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": 0.06360614553976156,
"min": 0.06360614553976156,
"max": 0.07677762399823633,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25442458215904623,
"min": 0.25442458215904623,
"max": 0.38388811999118166,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19493545285042596,
"min": 0.11707407088069172,
"max": 0.2972986241619961,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7797418114017038,
"min": 0.46829628352276687,
"max": 1.4482865304339165,
"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": 24.068181818181817,
"min": 3.3863636363636362,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1059.0,
"min": 149.0,
"max": 1343.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.068181818181817,
"min": 3.3863636363636362,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1059.0,
"min": 149.0,
"max": 1343.0,
"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": "1677791460",
"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": "1.22.4",
"end_time_seconds": "1677791942"
},
"total": 481.833033974,
"count": 1,
"self": 0.39309021399992616,
"children": {
"run_training.setup": {
"total": 0.11388686499998357,
"count": 1,
"self": 0.11388686499998357
},
"TrainerController.start_learning": {
"total": 481.3260568950001,
"count": 1,
"self": 0.586251816996878,
"children": {
"TrainerController._reset_env": {
"total": 9.874618091000002,
"count": 1,
"self": 9.874618091000002
},
"TrainerController.advance": {
"total": 470.7438685070032,
"count": 18203,
"self": 0.2999516459899496,
"children": {
"env_step": {
"total": 470.44391686101324,
"count": 18203,
"self": 326.7324806780171,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.4002874990034,
"count": 18203,
"self": 1.580669588002877,
"children": {
"TorchPolicy.evaluate": {
"total": 141.81961791100053,
"count": 18203,
"self": 32.2787024999983,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.54091541100223,
"count": 18203,
"self": 109.54091541100223
}
}
}
}
},
"workers": {
"total": 0.31114868399271245,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 479.67606685401114,
"count": 18203,
"is_parallel": true,
"self": 232.07233966500996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005548317000034331,
"count": 1,
"is_parallel": true,
"self": 0.0035679709999385523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019803460000957784,
"count": 10,
"is_parallel": true,
"self": 0.0019803460000957784
}
}
},
"UnityEnvironment.step": {
"total": 0.035669025999993664,
"count": 1,
"is_parallel": true,
"self": 0.00039579499997444145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033379000001332315,
"count": 1,
"is_parallel": true,
"self": 0.00033379000001332315
},
"communicator.exchange": {
"total": 0.03306161299997257,
"count": 1,
"is_parallel": true,
"self": 0.03306161299997257
},
"steps_from_proto": {
"total": 0.0018778280000333325,
"count": 1,
"is_parallel": true,
"self": 0.00040035400002125243,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00147747400001208,
"count": 10,
"is_parallel": true,
"self": 0.00147747400001208
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.60372718900118,
"count": 18202,
"is_parallel": true,
"self": 9.841226957002505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.456887402996244,
"count": 18202,
"is_parallel": true,
"self": 5.456887402996244
},
"communicator.exchange": {
"total": 199.5000456819974,
"count": 18202,
"is_parallel": true,
"self": 199.5000456819974
},
"steps_from_proto": {
"total": 32.805567147005036,
"count": 18202,
"is_parallel": true,
"self": 7.296832022986393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.508735124018642,
"count": 182020,
"is_parallel": true,
"self": 25.508735124018642
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013571500005582493,
"count": 1,
"self": 0.00013571500005582493,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 467.3035300979974,
"count": 412315,
"is_parallel": true,
"self": 10.303761173991177,
"children": {
"process_trajectory": {
"total": 267.34942032600577,
"count": 412315,
"is_parallel": true,
"self": 266.5148689570057,
"children": {
"RLTrainer._checkpoint": {
"total": 0.834551369000053,
"count": 4,
"is_parallel": true,
"self": 0.834551369000053
}
}
},
"_update_policy": {
"total": 189.65034859800045,
"count": 90,
"is_parallel": true,
"self": 67.90730229900134,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.7430462989991,
"count": 4587,
"is_parallel": true,
"self": 121.7430462989991
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12118276499995773,
"count": 1,
"self": 0.0008479109999370849,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12033485400002064,
"count": 1,
"self": 0.12033485400002064
}
}
}
}
}
}
}