jpopham91's picture
init
d61b7a9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0330536365509033,
"min": 1.0330536365509033,
"max": 2.859964609146118,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9931.77734375,
"min": 9931.77734375,
"max": 29288.8984375,
"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": 11.854769706726074,
"min": 0.14046762883663177,
"max": 11.854769706726074,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2311.68017578125,
"min": 27.250720977783203,
"max": 2411.3623046875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06978959247912737,
"min": 0.06100415595836809,
"max": 0.07197096968074237,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2791583699165095,
"min": 0.25661964742147236,
"max": 0.3598548484037119,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20431031681158962,
"min": 0.12007590244962452,
"max": 0.28066839548010447,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8172412672463585,
"min": 0.48030360979849807,
"max": 1.344962069509076,
"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": 23.613636363636363,
"min": 2.7954545454545454,
"max": 23.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1039.0,
"min": 123.0,
"max": 1297.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.613636363636363,
"min": 2.7954545454545454,
"max": 23.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1039.0,
"min": 123.0,
"max": 1297.0,
"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": "1673549706",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673550145"
},
"total": 438.660217201,
"count": 1,
"self": 0.3928408760001503,
"children": {
"run_training.setup": {
"total": 0.11970932399992762,
"count": 1,
"self": 0.11970932399992762
},
"TrainerController.start_learning": {
"total": 438.14766700099995,
"count": 1,
"self": 0.5626960340060805,
"children": {
"TrainerController._reset_env": {
"total": 9.231303597999954,
"count": 1,
"self": 9.231303597999954
},
"TrainerController.advance": {
"total": 428.2297213079938,
"count": 18210,
"self": 0.2716598009866402,
"children": {
"env_step": {
"total": 427.9580615070072,
"count": 18210,
"self": 280.0307576290023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.65372906599987,
"count": 18210,
"self": 1.3735138069978348,
"children": {
"TorchPolicy.evaluate": {
"total": 146.28021525900203,
"count": 18210,
"self": 31.986599481994404,
"children": {
"TorchPolicy.sample_actions": {
"total": 114.29361577700763,
"count": 18210,
"self": 114.29361577700763
}
}
}
}
},
"workers": {
"total": 0.2735748120049948,
"count": 18210,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.8767054129896,
"count": 18210,
"is_parallel": true,
"self": 211.25022061098343,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.012045830000033675,
"count": 1,
"is_parallel": true,
"self": 0.007481626000071628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0045642039999620465,
"count": 10,
"is_parallel": true,
"self": 0.0045642039999620465
}
}
},
"UnityEnvironment.step": {
"total": 0.051322385999924336,
"count": 1,
"is_parallel": true,
"self": 0.0005319559998042678,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042296900005567295,
"count": 1,
"is_parallel": true,
"self": 0.00042296900005567295
},
"communicator.exchange": {
"total": 0.048566281000034905,
"count": 1,
"is_parallel": true,
"self": 0.048566281000034905
},
"steps_from_proto": {
"total": 0.0018011800000294897,
"count": 1,
"is_parallel": true,
"self": 0.0004223830001137685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013787969999157212,
"count": 10,
"is_parallel": true,
"self": 0.0013787969999157212
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.6264848020062,
"count": 18209,
"is_parallel": true,
"self": 8.514010411993695,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.120807636995096,
"count": 18209,
"is_parallel": true,
"self": 5.120807636995096
},
"communicator.exchange": {
"total": 178.46137839200549,
"count": 18209,
"is_parallel": true,
"self": 178.46137839200549
},
"steps_from_proto": {
"total": 33.53028836101191,
"count": 18209,
"is_parallel": true,
"self": 6.848042812034123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.68224554897779,
"count": 182090,
"is_parallel": true,
"self": 26.68224554897779
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.580700010592409e-05,
"count": 1,
"self": 4.580700010592409e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 425.3083670069926,
"count": 342895,
"is_parallel": true,
"self": 9.111973448971185,
"children": {
"process_trajectory": {
"total": 243.5065582480214,
"count": 342895,
"is_parallel": true,
"self": 242.70026086102143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8062973869999723,
"count": 4,
"is_parallel": true,
"self": 0.8062973869999723
}
}
},
"_update_policy": {
"total": 172.68983531000003,
"count": 90,
"is_parallel": true,
"self": 46.36737260600455,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.32246270399548,
"count": 4587,
"is_parallel": true,
"self": 126.32246270399548
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1239002539999774,
"count": 1,
"self": 0.0010176600000022518,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12288259399997514,
"count": 1,
"self": 0.12288259399997514
}
}
}
}
}
}
}