zhangtemplar's picture
First Push
ed71623 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.848549485206604,
"min": 0.8303333520889282,
"max": 2.8563995361328125,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8064.6142578125,
"min": 8064.6142578125,
"max": 29158.126953125,
"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": 12.915194511413574,
"min": 0.3977316915988922,
"max": 12.915194511413574,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.462890625,
"min": 77.15995025634766,
"max": 2620.5673828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06999283893331748,
"min": 0.06263220731583287,
"max": 0.07516165673515905,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2799713557332699,
"min": 0.26231507904516294,
"max": 0.3587575056424648,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21133464691685694,
"min": 0.12219521188629134,
"max": 0.30077147797918785,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8453385876674278,
"min": 0.4887808475451654,
"max": 1.378263926096991,
"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": 25.40909090909091,
"min": 3.2045454545454546,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 141.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.2045454545454546,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 141.0,
"max": 1389.0,
"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": "1740953003",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740953441"
},
"total": 437.7801823719999,
"count": 1,
"self": 0.43164207299992086,
"children": {
"run_training.setup": {
"total": 0.024664260000008653,
"count": 1,
"self": 0.024664260000008653
},
"TrainerController.start_learning": {
"total": 437.32387603899997,
"count": 1,
"self": 0.3998202770071657,
"children": {
"TrainerController._reset_env": {
"total": 3.0638012260000096,
"count": 1,
"self": 3.0638012260000096
},
"TrainerController.advance": {
"total": 433.7725863069928,
"count": 18192,
"self": 0.39692029899515546,
"children": {
"env_step": {
"total": 307.5829370669919,
"count": 18192,
"self": 234.31585828598588,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.0343477960007,
"count": 18192,
"self": 1.3252482049972514,
"children": {
"TorchPolicy.evaluate": {
"total": 71.70909959100345,
"count": 18192,
"self": 71.70909959100345
}
}
},
"workers": {
"total": 0.2327309850053325,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.6820322609974,
"count": 18192,
"is_parallel": true,
"self": 230.86248577900597,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005541841999956887,
"count": 1,
"is_parallel": true,
"self": 0.004082871000036903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001458970999919984,
"count": 10,
"is_parallel": true,
"self": 0.001458970999919984
}
}
},
"UnityEnvironment.step": {
"total": 0.037209673999996085,
"count": 1,
"is_parallel": true,
"self": 0.0005571049998707167,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036599400004888594,
"count": 1,
"is_parallel": true,
"self": 0.00036599400004888594
},
"communicator.exchange": {
"total": 0.03442912200000592,
"count": 1,
"is_parallel": true,
"self": 0.03442912200000592
},
"steps_from_proto": {
"total": 0.0018574530000705636,
"count": 1,
"is_parallel": true,
"self": 0.0003545580000263726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001502895000044191,
"count": 10,
"is_parallel": true,
"self": 0.001502895000044191
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.81954648199144,
"count": 18191,
"is_parallel": true,
"self": 9.58672395698511,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.301844280012801,
"count": 18191,
"is_parallel": true,
"self": 5.301844280012801
},
"communicator.exchange": {
"total": 158.72917820599946,
"count": 18191,
"is_parallel": true,
"self": 158.72917820599946
},
"steps_from_proto": {
"total": 31.201800038994065,
"count": 18191,
"is_parallel": true,
"self": 5.661657090992776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.54014294800129,
"count": 181910,
"is_parallel": true,
"self": 25.54014294800129
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.79272894100575,
"count": 18192,
"self": 0.49306955800022934,
"children": {
"process_trajectory": {
"total": 27.040731542005688,
"count": 18192,
"self": 26.45919012200568,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5815414200000077,
"count": 4,
"self": 0.5815414200000077
}
}
},
"_update_policy": {
"total": 98.25892784099983,
"count": 90,
"self": 39.494884481005556,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.764043359994275,
"count": 4587,
"self": 58.764043359994275
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.08766736699999456,
"count": 1,
"self": 0.0009155499999451422,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08675181700004941,
"count": 1,
"self": 0.08675181700004941
}
}
}
}
}
}
}