emmuzoo's picture
basic model
c5bd0e5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0075739622116089,
"min": 0.975491464138031,
"max": 2.854794502258301,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9642.482421875,
"min": 9642.482421875,
"max": 29330.158203125,
"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": 11.752942085266113,
"min": 0.31435027718544006,
"max": 11.773415565490723,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2291.82373046875,
"min": 60.983951568603516,
"max": 2401.77685546875,
"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": 0.06968696768536556,
"min": 0.06428110851879418,
"max": 0.07654687728842391,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27874787074146223,
"min": 0.2571244340751767,
"max": 0.38273438644211955,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1758650505878762,
"min": 0.09644893987912356,
"max": 0.28617184769873527,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7034602023515047,
"min": 0.38579575951649425,
"max": 1.4095401387004292,
"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": 22.90909090909091,
"min": 3.0681818181818183,
"max": 23.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1008.0,
"min": 135.0,
"max": 1288.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.90909090909091,
"min": 3.0681818181818183,
"max": 23.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1008.0,
"min": 135.0,
"max": 1288.0,
"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": "1679773762",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679774235"
},
"total": 473.30732524099994,
"count": 1,
"self": 0.4930751229999828,
"children": {
"run_training.setup": {
"total": 0.1291536219999898,
"count": 1,
"self": 0.1291536219999898
},
"TrainerController.start_learning": {
"total": 472.68509649599997,
"count": 1,
"self": 0.5738894569973354,
"children": {
"TrainerController._reset_env": {
"total": 9.373357095000017,
"count": 1,
"self": 9.373357095000017
},
"TrainerController.advance": {
"total": 462.5203482940027,
"count": 18215,
"self": 0.28060907600502105,
"children": {
"env_step": {
"total": 462.2397392179977,
"count": 18215,
"self": 334.2688867730063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.69723372699309,
"count": 18215,
"self": 2.632783560991072,
"children": {
"TorchPolicy.evaluate": {
"total": 125.06445016600202,
"count": 18215,
"self": 125.06445016600202
}
}
},
"workers": {
"total": 0.2736187179983176,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.1591096800036,
"count": 18215,
"is_parallel": true,
"self": 222.43252904300698,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005744782000022042,
"count": 1,
"is_parallel": true,
"self": 0.0036553879999132732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020893940001087685,
"count": 10,
"is_parallel": true,
"self": 0.0020893940001087685
}
}
},
"UnityEnvironment.step": {
"total": 0.04599177699998336,
"count": 1,
"is_parallel": true,
"self": 0.0005862639999918429,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038154899999653935,
"count": 1,
"is_parallel": true,
"self": 0.00038154899999653935
},
"communicator.exchange": {
"total": 0.04323897099999385,
"count": 1,
"is_parallel": true,
"self": 0.04323897099999385
},
"steps_from_proto": {
"total": 0.0017849930000011227,
"count": 1,
"is_parallel": true,
"self": 0.000366859999985536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014181330000155867,
"count": 10,
"is_parallel": true,
"self": 0.0014181330000155867
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.72658063699663,
"count": 18214,
"is_parallel": true,
"self": 9.714633763981112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.20376024601012,
"count": 18214,
"is_parallel": true,
"self": 5.20376024601012
},
"communicator.exchange": {
"total": 202.14032614700022,
"count": 18214,
"is_parallel": true,
"self": 202.14032614700022
},
"steps_from_proto": {
"total": 31.667860480005174,
"count": 18214,
"is_parallel": true,
"self": 6.242566093013522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.425294386991652,
"count": 182140,
"is_parallel": true,
"self": 25.425294386991652
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001249239999197016,
"count": 1,
"self": 0.0001249239999197016,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.0341866520034,
"count": 418461,
"is_parallel": true,
"self": 10.124565329944915,
"children": {
"process_trajectory": {
"total": 255.30153301505817,
"count": 418461,
"is_parallel": true,
"self": 253.48102052405812,
"children": {
"RLTrainer._checkpoint": {
"total": 1.820512491000045,
"count": 4,
"is_parallel": true,
"self": 1.820512491000045
}
}
},
"_update_policy": {
"total": 193.60808830700034,
"count": 90,
"is_parallel": true,
"self": 70.58840473000089,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.01968357699945,
"count": 4587,
"is_parallel": true,
"self": 123.01968357699945
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2173767259999977,
"count": 1,
"self": 0.0011468689999674098,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21622985700003028,
"count": 1,
"self": 0.21622985700003028
}
}
}
}
}
}
}