ArunKr's picture
First Push
e886ecc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7895591855049133,
"min": 0.7895591855049133,
"max": 2.8541131019592285,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7503.970703125,
"min": 7503.970703125,
"max": 29134.787109375,
"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": 12.682629585266113,
"min": 0.3877338469028473,
"max": 12.682629585266113,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2473.11279296875,
"min": 75.22036743164062,
"max": 2551.724609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07093675941909097,
"min": 0.06009494362328862,
"max": 0.07356826945382922,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2837470376763639,
"min": 0.26354065747000277,
"max": 0.36412521268471654,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20016825147995762,
"min": 0.11761161739431211,
"max": 0.29148450544944,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8006730059198305,
"min": 0.47044646957724845,
"max": 1.3496129179702085,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.318181818181817,
"min": 3.5,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 154.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.5,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 154.0,
"max": 1385.0,
"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": "1755410822",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1755411308"
},
"total": 485.8549739140001,
"count": 1,
"self": 0.5387041670001054,
"children": {
"run_training.setup": {
"total": 0.028521965999971144,
"count": 1,
"self": 0.028521965999971144
},
"TrainerController.start_learning": {
"total": 485.287747781,
"count": 1,
"self": 0.5246636469983059,
"children": {
"TrainerController._reset_env": {
"total": 2.855670410000016,
"count": 1,
"self": 2.855670410000016
},
"TrainerController.advance": {
"total": 481.8383048790016,
"count": 18192,
"self": 0.5050725070142335,
"children": {
"env_step": {
"total": 333.7855875180004,
"count": 18192,
"self": 285.0147796099809,
"children": {
"SubprocessEnvManager._take_step": {
"total": 48.4670090790097,
"count": 18192,
"self": 1.4970898200077727,
"children": {
"TorchPolicy.evaluate": {
"total": 46.96991925900193,
"count": 18192,
"self": 46.96991925900193
}
}
},
"workers": {
"total": 0.3037988290097928,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 483.6494255890009,
"count": 18192,
"is_parallel": true,
"self": 234.73142555699803,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006341652999935832,
"count": 1,
"is_parallel": true,
"self": 0.004601613999625442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017400390003103894,
"count": 10,
"is_parallel": true,
"self": 0.0017400390003103894
}
}
},
"UnityEnvironment.step": {
"total": 0.05227806300001703,
"count": 1,
"is_parallel": true,
"self": 0.0006934460001275511,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045033599997168494,
"count": 1,
"is_parallel": true,
"self": 0.00045033599997168494
},
"communicator.exchange": {
"total": 0.04901007099999788,
"count": 1,
"is_parallel": true,
"self": 0.04901007099999788
},
"steps_from_proto": {
"total": 0.0021242099999199127,
"count": 1,
"is_parallel": true,
"self": 0.000427038000225366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016971719996945467,
"count": 10,
"is_parallel": true,
"self": 0.0016971719996945467
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.91800003200285,
"count": 18191,
"is_parallel": true,
"self": 11.741166251013738,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.428823308981691,
"count": 18191,
"is_parallel": true,
"self": 6.428823308981691
},
"communicator.exchange": {
"total": 193.8669887460146,
"count": 18191,
"is_parallel": true,
"self": 193.8669887460146
},
"steps_from_proto": {
"total": 36.88102172599281,
"count": 18191,
"is_parallel": true,
"self": 6.879456640984358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.00156508500845,
"count": 181910,
"is_parallel": true,
"self": 30.00156508500845
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 147.54764485398698,
"count": 18192,
"self": 0.6785945599691559,
"children": {
"process_trajectory": {
"total": 26.643940117017337,
"count": 18192,
"self": 26.3070194840177,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3369206329996359,
"count": 4,
"self": 0.3369206329996359
}
}
},
"_update_policy": {
"total": 120.22511017700049,
"count": 90,
"self": 45.036990509002294,
"children": {
"TorchPPOOptimizer.update": {
"total": 75.1881196679982,
"count": 4587,
"self": 75.1881196679982
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0520000159885967e-06,
"count": 1,
"self": 1.0520000159885967e-06
},
"TrainerController._save_models": {
"total": 0.06910779300005743,
"count": 1,
"self": 0.0009935119999227027,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06811428100013472,
"count": 1,
"self": 0.06811428100013472
}
}
}
}
}
}
}