conorbranagan's picture
First Push
2b72682 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9059039354324341,
"min": 0.9059039354324341,
"max": 2.8290483951568604,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8609.7109375,
"min": 8609.7109375,
"max": 28878.92578125,
"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": 12.98824405670166,
"min": 0.46341559290885925,
"max": 12.98824405670166,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.70751953125,
"min": 89.90262603759766,
"max": 2637.22216796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06885176249329115,
"min": 0.062250117366456116,
"max": 0.08028946622924231,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2754070499731646,
"min": 0.26840148654232243,
"max": 0.36088561336681085,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1975071113921848,
"min": 0.15350983060175077,
"max": 0.31205571640063734,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7900284455687392,
"min": 0.6140393224070031,
"max": 1.4046173785247056,
"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": 25.545454545454547,
"min": 4.4772727272727275,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 197.0,
"max": 1417.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 4.4772727272727275,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 197.0,
"max": 1417.0,
"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": "1740432106",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740432545"
},
"total": 439.26251761899994,
"count": 1,
"self": 0.4356502820000969,
"children": {
"run_training.setup": {
"total": 0.02345375499999136,
"count": 1,
"self": 0.02345375499999136
},
"TrainerController.start_learning": {
"total": 438.80341358199985,
"count": 1,
"self": 0.36305669300713816,
"children": {
"TrainerController._reset_env": {
"total": 3.3621072060000188,
"count": 1,
"self": 3.3621072060000188
},
"TrainerController.advance": {
"total": 434.98538488699273,
"count": 18192,
"self": 0.35914763398432115,
"children": {
"env_step": {
"total": 311.36627272200167,
"count": 18192,
"self": 236.7124745219719,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.44380506199263,
"count": 18192,
"self": 1.3096725579862323,
"children": {
"TorchPolicy.evaluate": {
"total": 73.1341325040064,
"count": 18192,
"self": 73.1341325040064
}
}
},
"workers": {
"total": 0.20999313803713449,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.2394116439932,
"count": 18192,
"is_parallel": true,
"self": 229.45975119098875,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005793584999992163,
"count": 1,
"is_parallel": true,
"self": 0.004135864000090805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016577209999013576,
"count": 10,
"is_parallel": true,
"self": 0.0016577209999013576
}
}
},
"UnityEnvironment.step": {
"total": 0.07342665800001669,
"count": 1,
"is_parallel": true,
"self": 0.0006996469999194233,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005033649999859335,
"count": 1,
"is_parallel": true,
"self": 0.0005033649999859335
},
"communicator.exchange": {
"total": 0.07018461900020156,
"count": 1,
"is_parallel": true,
"self": 0.07018461900020156
},
"steps_from_proto": {
"total": 0.0020390269999097654,
"count": 1,
"is_parallel": true,
"self": 0.00037145200008126267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016675749998285028,
"count": 10,
"is_parallel": true,
"self": 0.0016675749998285028
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.77966045300445,
"count": 18191,
"is_parallel": true,
"self": 10.088039053993953,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.590676150999116,
"count": 18191,
"is_parallel": true,
"self": 5.590676150999116
},
"communicator.exchange": {
"total": 159.1097157839938,
"count": 18191,
"is_parallel": true,
"self": 159.1097157839938
},
"steps_from_proto": {
"total": 32.99122946401758,
"count": 18191,
"is_parallel": true,
"self": 5.860627147006653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.130602317010926,
"count": 181910,
"is_parallel": true,
"self": 27.130602317010926
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.25996453100674,
"count": 18192,
"self": 0.44203000300717576,
"children": {
"process_trajectory": {
"total": 27.31066597299923,
"count": 18192,
"self": 26.77357818399946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.53708778899977,
"count": 4,
"self": 0.53708778899977
}
}
},
"_update_policy": {
"total": 95.50726855500034,
"count": 90,
"self": 38.11194504099558,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.39532351400476,
"count": 4587,
"self": 57.39532351400476
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3159999525669264e-06,
"count": 1,
"self": 1.3159999525669264e-06
},
"TrainerController._save_models": {
"total": 0.09286348000000544,
"count": 1,
"self": 0.0010193699999945238,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09184411000001091,
"count": 1,
"self": 0.09184411000001091
}
}
}
}
}
}
}