xiazeng's picture
First Push
60de8b8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9822655916213989,
"min": 0.9822655916213989,
"max": 2.8533835411071777,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9378.671875,
"min": 9378.671875,
"max": 29221.501953125,
"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": 12.438921928405762,
"min": 0.3473450839519501,
"max": 12.438921928405762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2425.58984375,
"min": 67.38494873046875,
"max": 2532.43798828125,
"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": 0.06965872041965829,
"min": 0.06362817695495039,
"max": 0.07786119005550954,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27863488167863315,
"min": 0.25451270781980156,
"max": 0.37556518466433275,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20081154337408497,
"min": 0.13235547381804746,
"max": 0.29316510265948725,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8032461734963399,
"min": 0.5294218952721899,
"max": 1.4658255132974363,
"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": 3.6136363636363638,
"max": 24.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1059.0,
"min": 159.0,
"max": 1374.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.068181818181817,
"min": 3.6136363636363638,
"max": 24.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1059.0,
"min": 159.0,
"max": 1374.0,
"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": "1676138292",
"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": "1.21.6",
"end_time_seconds": "1676138743"
},
"total": 450.865449803,
"count": 1,
"self": 0.4279447709999431,
"children": {
"run_training.setup": {
"total": 0.19409082900000385,
"count": 1,
"self": 0.19409082900000385
},
"TrainerController.start_learning": {
"total": 450.24341420300004,
"count": 1,
"self": 0.5365781259953906,
"children": {
"TrainerController._reset_env": {
"total": 8.93680044399997,
"count": 1,
"self": 8.93680044399997
},
"TrainerController.advance": {
"total": 440.65062514000465,
"count": 18203,
"self": 0.25739711201077853,
"children": {
"env_step": {
"total": 440.39322802799387,
"count": 18203,
"self": 303.73534026101163,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.4068349969952,
"count": 18203,
"self": 1.5640808479836323,
"children": {
"TorchPolicy.evaluate": {
"total": 134.84275414901157,
"count": 18203,
"self": 29.938392693005824,
"children": {
"TorchPolicy.sample_actions": {
"total": 104.90436145600574,
"count": 18203,
"self": 104.90436145600574
}
}
}
}
},
"workers": {
"total": 0.25105276998704085,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.90718173300456,
"count": 18203,
"is_parallel": true,
"self": 216.37136387498578,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006514371000037045,
"count": 1,
"is_parallel": true,
"self": 0.0036133780000682236,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002900992999968821,
"count": 10,
"is_parallel": true,
"self": 0.002900992999968821
}
}
},
"UnityEnvironment.step": {
"total": 0.044903038999962064,
"count": 1,
"is_parallel": true,
"self": 0.0004457520000187287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041323399995008003,
"count": 1,
"is_parallel": true,
"self": 0.00041323399995008003
},
"communicator.exchange": {
"total": 0.04145733799998652,
"count": 1,
"is_parallel": true,
"self": 0.04145733799998652
},
"steps_from_proto": {
"total": 0.002586715000006734,
"count": 1,
"is_parallel": true,
"self": 0.0006855200000472905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019011949999594435,
"count": 10,
"is_parallel": true,
"self": 0.0019011949999594435
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.5358178580188,
"count": 18202,
"is_parallel": true,
"self": 9.262006875018017,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.030340315989463,
"count": 18202,
"is_parallel": true,
"self": 5.030340315989463
},
"communicator.exchange": {
"total": 184.64326394600653,
"count": 18202,
"is_parallel": true,
"self": 184.64326394600653
},
"steps_from_proto": {
"total": 33.60020672100478,
"count": 18202,
"is_parallel": true,
"self": 6.772342751013184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.827863969991597,
"count": 182020,
"is_parallel": true,
"self": 26.827863969991597
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016488200003550446,
"count": 1,
"self": 0.00016488200003550446,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 437.3684980549866,
"count": 405468,
"is_parallel": true,
"self": 9.854839231998824,
"children": {
"process_trajectory": {
"total": 251.9753454179875,
"count": 405468,
"is_parallel": true,
"self": 251.1966806209876,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7786647969999194,
"count": 4,
"is_parallel": true,
"self": 0.7786647969999194
}
}
},
"_update_policy": {
"total": 175.53831340500028,
"count": 90,
"is_parallel": true,
"self": 59.81392365899916,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.72438974600112,
"count": 4587,
"is_parallel": true,
"self": 115.72438974600112
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11924561099999664,
"count": 1,
"self": 0.0009168510000563401,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1183287599999403,
"count": 1,
"self": 0.1183287599999403
}
}
}
}
}
}
}