magnustragardh's picture
First training of SnowballTarget
1e2478d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.891025722026825,
"min": 0.891025722026825,
"max": 2.868452310562134,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8546.71875,
"min": 8546.71875,
"max": 29502.03125,
"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": 12.865605354309082,
"min": 0.3067726194858551,
"max": 12.865605354309082,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.79296875,
"min": 59.513885498046875,
"max": 2596.06787109375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07042172840567004,
"min": 0.05815743528070444,
"max": 0.07439628877899154,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28168691362268017,
"min": 0.23262974112281776,
"max": 0.37024865522121836,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18690101466342512,
"min": 0.125361590529792,
"max": 0.2889059807593916,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7476040586537005,
"min": 0.501446362119168,
"max": 1.3722870916712517,
"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": 25.59090909090909,
"min": 3.3181818181818183,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 146.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.3181818181818183,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 146.0,
"max": 1400.0,
"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": "1688304279",
"python_version": "3.10.12 (main, Jun 9 2023, 20:10:04) [GCC 13.1.1 20230522 [revision dd36656ada05731c069ecd5b1878380294fb1f3e]]",
"command_line_arguments": "/home/magnus/.local/venv/ml-agents/bin/mlagents-learn --force config/ppo/SnowballTarget.yaml --env training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --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": "1688304535"
},
"total": 255.31354765300057,
"count": 1,
"self": 0.3685104140022304,
"children": {
"run_training.setup": {
"total": 0.007466240998837748,
"count": 1,
"self": 0.007466240998837748
},
"TrainerController.start_learning": {
"total": 254.9375709979995,
"count": 1,
"self": 0.3116893770693423,
"children": {
"TrainerController._reset_env": {
"total": 2.912570896000034,
"count": 1,
"self": 2.912570896000034
},
"TrainerController.advance": {
"total": 251.6296939659278,
"count": 18204,
"self": 0.15497213598246162,
"children": {
"env_step": {
"total": 251.47472182994534,
"count": 18204,
"self": 190.43396250896876,
"children": {
"SubprocessEnvManager._take_step": {
"total": 60.873841612989054,
"count": 18204,
"self": 0.7698521298989363,
"children": {
"TorchPolicy.evaluate": {
"total": 60.10398948309012,
"count": 18204,
"self": 60.10398948309012
}
}
},
"workers": {
"total": 0.1669177079875226,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 254.4974096430742,
"count": 18204,
"is_parallel": true,
"self": 118.09584323717718,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006279802999415551,
"count": 1,
"is_parallel": true,
"self": 0.005433346997961053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008464560014544986,
"count": 10,
"is_parallel": true,
"self": 0.0008464560014544986
}
}
},
"UnityEnvironment.step": {
"total": 0.01941664399964793,
"count": 1,
"is_parallel": true,
"self": 0.0005989729997963877,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015374599934148137,
"count": 1,
"is_parallel": true,
"self": 0.00015374599934148137
},
"communicator.exchange": {
"total": 0.016665812001519953,
"count": 1,
"is_parallel": true,
"self": 0.016665812001519953
},
"steps_from_proto": {
"total": 0.001998112998990109,
"count": 1,
"is_parallel": true,
"self": 0.00030572599462175276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016923870043683564,
"count": 10,
"is_parallel": true,
"self": 0.0016923870043683564
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 136.40156640589703,
"count": 18203,
"is_parallel": true,
"self": 7.011155038037032,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.7374462148673047,
"count": 18203,
"is_parallel": true,
"self": 2.7374462148673047
},
"communicator.exchange": {
"total": 106.22853367096104,
"count": 18203,
"is_parallel": true,
"self": 106.22853367096104
},
"steps_from_proto": {
"total": 20.42443148203165,
"count": 18203,
"is_parallel": true,
"self": 3.1778750075245625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.246556474507088,
"count": 182030,
"is_parallel": true,
"self": 17.246556474507088
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.56940007704543e-05,
"count": 1,
"self": 7.56940007704543e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 251.3545660198215,
"count": 142724,
"is_parallel": true,
"self": 1.4126219469071657,
"children": {
"process_trajectory": {
"total": 143.67994696892129,
"count": 142724,
"is_parallel": true,
"self": 143.18751019792035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4924367710009392,
"count": 4,
"is_parallel": true,
"self": 0.4924367710009392
}
}
},
"_update_policy": {
"total": 106.26199710399305,
"count": 90,
"is_parallel": true,
"self": 29.63671002295814,
"children": {
"TorchPPOOptimizer.update": {
"total": 76.62528708103491,
"count": 4587,
"is_parallel": true,
"self": 76.62528708103491
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08354106500155467,
"count": 1,
"self": 0.00038795800173829775,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08315310699981637,
"count": 1,
"self": 0.08315310699981637
}
}
}
}
}
}
}