{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7885963916778564, "min": 0.7885963916778564, "max": 2.8640334606170654, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7529.5185546875, "min": 7529.5185546875, "max": 29362.0703125, "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": 12.693319320678711, "min": 0.32494497299194336, "max": 12.697495460510254, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2475.197265625, "min": 63.03932571411133, "max": 2590.2890625, "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": 0.06317062387254327, "min": 0.06215785096853734, "max": 0.07700711763141489, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2526824954901731, "min": 0.2526824954901731, "max": 0.37711804982174335, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18711620872365492, "min": 0.1361283569541924, "max": 0.2799374065270611, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7484648348946197, "min": 0.5445134278167696, "max": 1.3696440294677135, "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": 24.886363636363637, "min": 3.5, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 154.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 3.5, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 154.0, "max": 1388.0, "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": "1679890580", "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": "1679891040" }, "total": 460.13870883899995, "count": 1, "self": 0.43997803699988935, "children": { "run_training.setup": { "total": 0.10745266100002482, "count": 1, "self": 0.10745266100002482 }, "TrainerController.start_learning": { "total": 459.59127814100003, "count": 1, "self": 0.5888360000020612, "children": { "TrainerController._reset_env": { "total": 9.011366586999998, "count": 1, "self": 9.011366586999998 }, "TrainerController.advance": { "total": 449.8620425869979, "count": 18202, "self": 0.2701485479953476, "children": { "env_step": { "total": 449.59189403900257, "count": 18202, "self": 323.76380178500176, "children": { "SubprocessEnvManager._take_step": { "total": 125.5615996089989, "count": 18202, "self": 2.305366731994127, "children": { "TorchPolicy.evaluate": { "total": 123.25623287700478, "count": 18202, "self": 123.25623287700478 } } }, "workers": { "total": 0.26649264500190384, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 458.1161150539984, "count": 18202, "is_parallel": true, "self": 220.52233719600184, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006856305999974666, "count": 1, "is_parallel": true, "self": 0.004556171000103859, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023001349998708065, "count": 10, "is_parallel": true, "self": 0.0023001349998708065 } } }, "UnityEnvironment.step": { "total": 0.07518376699999862, "count": 1, "is_parallel": true, "self": 0.0005536980000329095, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003804809999792269, "count": 1, "is_parallel": true, "self": 0.0003804809999792269 }, "communicator.exchange": { "total": 0.07251213600000028, "count": 1, "is_parallel": true, "self": 0.07251213600000028 }, "steps_from_proto": { "total": 0.001737451999986206, "count": 1, "is_parallel": true, "self": 0.0003258710001432519, "children": { "_process_rank_one_or_two_observation": { "total": 0.001411580999842954, "count": 10, "is_parallel": true, "self": 0.001411580999842954 } } } } } } }, "UnityEnvironment.step": { "total": 237.59377785799654, "count": 18201, "is_parallel": true, "self": 9.509541667994142, "children": { "UnityEnvironment._generate_step_input": { "total": 5.090437026008999, "count": 18201, "is_parallel": true, "self": 5.090437026008999 }, "communicator.exchange": { "total": 192.64797989999187, "count": 18201, "is_parallel": true, "self": 192.64797989999187 }, "steps_from_proto": { "total": 30.345819264001534, "count": 18201, "is_parallel": true, "self": 5.99622662402254, "children": { "_process_rank_one_or_two_observation": { "total": 24.349592639978994, "count": 182010, "is_parallel": true, "self": 24.349592639978994 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014805600005729502, "count": 1, "self": 0.00014805600005729502, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.4031134889945, "count": 405226, "is_parallel": true, "self": 10.249975915021707, "children": { "process_trajectory": { "total": 248.54555728097245, "count": 405226, "is_parallel": true, "self": 247.44766555797253, "children": { "RLTrainer._checkpoint": { "total": 1.0978917229999183, "count": 4, "is_parallel": true, "self": 1.0978917229999183 } } }, "_update_policy": { "total": 187.60758029300035, "count": 90, "is_parallel": true, "self": 66.10038895200296, "children": { "TorchPPOOptimizer.update": { "total": 121.5071913409974, "count": 4587, "is_parallel": true, "self": 121.5071913409974 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1288849110000001, "count": 1, "self": 0.000909975000013219, "children": { "RLTrainer._checkpoint": { "total": 0.12797493599998688, "count": 1, "self": 0.12797493599998688 } } } } } } }