{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8354091644287109, "min": 0.8354091644287109, "max": 2.8675858974456787, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7976.48681640625, "min": 7976.48681640625, "max": 29366.947265625, "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": 13.013903617858887, "min": 0.2829882502555847, "max": 13.018391609191895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.711181640625, "min": 54.89971923828125, "max": 2647.64013671875, "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": 0.061025708106992135, "min": 0.061025708106992135, "max": 0.07724372483390456, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24410283242796854, "min": 0.24410283242796854, "max": 0.3690536568716269, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20854443015859409, "min": 0.09148832632105469, "max": 0.30427866402794335, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8341777206343763, "min": 0.36595330528421877, "max": 1.5213933201397167, "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": 25.454545454545453, "min": 2.7045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 119.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 2.7045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 119.0, "max": 1391.0, "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": "1677936430", "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": "1.22.4", "end_time_seconds": "1677936917" }, "total": 486.5087132440001, "count": 1, "self": 0.45155297800010885, "children": { "run_training.setup": { "total": 0.18331310899998243, "count": 1, "self": 0.18331310899998243 }, "TrainerController.start_learning": { "total": 485.873847157, "count": 1, "self": 0.6221097649965941, "children": { "TrainerController._reset_env": { "total": 9.415352491000021, "count": 1, "self": 9.415352491000021 }, "TrainerController.advance": { "total": 475.71150847700324, "count": 18202, "self": 0.3003628630112871, "children": { "env_step": { "total": 475.41114561399195, "count": 18202, "self": 334.069768056979, "children": { "SubprocessEnvManager._take_step": { "total": 141.05698832299754, "count": 18202, "self": 1.5970300580083858, "children": { "TorchPolicy.evaluate": { "total": 139.45995826498915, "count": 18202, "self": 31.71141396199573, "children": { "TorchPolicy.sample_actions": { "total": 107.74854430299342, "count": 18202, "self": 107.74854430299342 } } } } }, "workers": { "total": 0.28438923401540706, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 484.0678001799922, "count": 18202, "is_parallel": true, "self": 234.19198673198457, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006429706000062652, "count": 1, "is_parallel": true, "self": 0.004201753999723223, "children": { "_process_rank_one_or_two_observation": { "total": 0.002227952000339428, "count": 10, "is_parallel": true, "self": 0.002227952000339428 } } }, "UnityEnvironment.step": { "total": 0.04760322299989639, "count": 1, "is_parallel": true, "self": 0.00034255399964422395, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030535300015799294, "count": 1, "is_parallel": true, "self": 0.00030535300015799294 }, "communicator.exchange": { "total": 0.045707775999972, "count": 1, "is_parallel": true, "self": 0.045707775999972 }, "steps_from_proto": { "total": 0.0012475400001221715, "count": 1, "is_parallel": true, "self": 0.0002904880004734878, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009570519996486837, "count": 10, "is_parallel": true, "self": 0.0009570519996486837 } } } } } } }, "UnityEnvironment.step": { "total": 249.87581344800765, "count": 18201, "is_parallel": true, "self": 9.910772598991798, "children": { "UnityEnvironment._generate_step_input": { "total": 5.39953131001198, "count": 18201, "is_parallel": true, "self": 5.39953131001198 }, "communicator.exchange": { "total": 202.4098650289891, "count": 18201, "is_parallel": true, "self": 202.4098650289891 }, "steps_from_proto": { "total": 32.15564451001478, "count": 18201, "is_parallel": true, "self": 7.140624258047637, "children": { "_process_rank_one_or_two_observation": { "total": 25.015020251967144, "count": 182010, "is_parallel": true, "self": 25.015020251967144 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000129326000205765, "count": 1, "self": 0.000129326000205765, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.1654870149432, "count": 442963, "is_parallel": true, "self": 10.49348944385224, "children": { "process_trajectory": { "total": 270.6027887960918, "count": 442963, "is_parallel": true, "self": 269.5708522530915, "children": { "RLTrainer._checkpoint": { "total": 1.0319365430002563, "count": 4, "is_parallel": true, "self": 1.0319365430002563 } } }, "_update_policy": { "total": 191.0692087749992, "count": 90, "is_parallel": true, "self": 74.1718099789889, "children": { "TorchPPOOptimizer.update": { "total": 116.8973987960103, "count": 4587, "is_parallel": true, "self": 116.8973987960103 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12474709799994343, "count": 1, "self": 0.0009118779998971149, "children": { "RLTrainer._checkpoint": { "total": 0.12383522000004632, "count": 1, "self": 0.12383522000004632 } } } } } } }