{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0339924097061157, "min": 1.0339924097061157, "max": 2.85452938079834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9872.5595703125, "min": 9872.5595703125, "max": 29201.8359375, "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": 13.018086433410645, "min": 0.44489458203315735, "max": 13.018086433410645, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.52685546875, "min": 86.3095474243164, "max": 2650.89013671875, "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": 0.07337979286539313, "min": 0.06017116539730398, "max": 0.07485646008806048, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2935191714615725, "min": 0.2534319986355281, "max": 0.37428230044030236, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2149646497678523, "min": 0.1354475204088707, "max": 0.2573793529879813, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8598585990714092, "min": 0.5417900816354828, "max": 1.2868967649399066, "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": 25.727272727272727, "min": 3.5681818181818183, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 157.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.5681818181818183, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 157.0, "max": 1403.0, "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": "1674141297", "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": "1674141727" }, "total": 430.162545419, "count": 1, "self": 0.4353647960000444, "children": { "run_training.setup": { "total": 0.10408757799996238, "count": 1, "self": 0.10408757799996238 }, "TrainerController.start_learning": { "total": 429.623093045, "count": 1, "self": 0.5577737839969359, "children": { "TrainerController._reset_env": { "total": 9.558048815999996, "count": 1, "self": 9.558048815999996 }, "TrainerController.advance": { "total": 419.38478311600306, "count": 18201, "self": 0.265879952004866, "children": { "env_step": { "total": 419.1189031639982, "count": 18201, "self": 275.13952319400937, "children": { "SubprocessEnvManager._take_step": { "total": 143.71560684699654, "count": 18201, "self": 1.3716741459966215, "children": { "TorchPolicy.evaluate": { "total": 142.34393270099991, "count": 18201, "self": 31.609398811994822, "children": { "TorchPolicy.sample_actions": { "total": 110.73453388900509, "count": 18201, "self": 110.73453388900509 } } } } }, "workers": { "total": 0.2637731229922906, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 428.43096725899824, "count": 18201, "is_parallel": true, "self": 206.1386754910015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005783760999975129, "count": 1, "is_parallel": true, "self": 0.003561012999966806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022227480000083233, "count": 10, "is_parallel": true, "self": 0.0022227480000083233 } } }, "UnityEnvironment.step": { "total": 0.03849694199999476, "count": 1, "is_parallel": true, "self": 0.0005080509999970673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002725169999848731, "count": 1, "is_parallel": true, "self": 0.0002725169999848731 }, "communicator.exchange": { "total": 0.03577321000000211, "count": 1, "is_parallel": true, "self": 0.03577321000000211 }, "steps_from_proto": { "total": 0.0019431640000107109, "count": 1, "is_parallel": true, "self": 0.00044376099998544305, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014994030000252678, "count": 10, "is_parallel": true, "self": 0.0014994030000252678 } } } } } } }, "UnityEnvironment.step": { "total": 222.29229176799674, "count": 18200, "is_parallel": true, "self": 8.299762779004823, "children": { "UnityEnvironment._generate_step_input": { "total": 4.874267608996092, "count": 18200, "is_parallel": true, "self": 4.874267608996092 }, "communicator.exchange": { "total": 177.09563308999105, "count": 18200, "is_parallel": true, "self": 177.09563308999105 }, "steps_from_proto": { "total": 32.022628290004775, "count": 18200, "is_parallel": true, "self": 6.456097577992637, "children": { "_process_rank_one_or_two_observation": { "total": 25.56653071201214, "count": 182000, "is_parallel": true, "self": 25.56653071201214 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.390700007661508e-05, "count": 1, "self": 4.390700007661508e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 416.2794221650061, "count": 344087, "is_parallel": true, "self": 8.932873767003741, "children": { "process_trajectory": { "total": 238.73715096500302, "count": 344087, "is_parallel": true, "self": 238.06061432400327, "children": { "RLTrainer._checkpoint": { "total": 0.6765366409997569, "count": 4, "is_parallel": true, "self": 0.6765366409997569 } } }, "_update_policy": { "total": 168.60939743299934, "count": 90, "is_parallel": true, "self": 43.44768647100068, "children": { "TorchPPOOptimizer.update": { "total": 125.16171096199866, "count": 4587, "is_parallel": true, "self": 125.16171096199866 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12244342199994662, "count": 1, "self": 0.0008704649999344838, "children": { "RLTrainer._checkpoint": { "total": 0.12157295700001214, "count": 1, "self": 0.12157295700001214 } } } } } } }