{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050995111465454, "min": 1.4050995111465454, "max": 1.4282584190368652, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72609.921875, "min": 66740.90625, "max": 76427.625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 116.0304449648712, "min": 88.46153846153847, "max": 404.7016129032258, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49545.0, "min": 48931.0, "max": 50183.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999929.0, "min": 49803.0, "max": 1999929.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999929.0, "min": 49803.0, "max": 1999929.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4248344898223877, "min": 0.010575092397630215, "max": 2.435241222381592, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1035.404296875, "min": 1.3007363080978394, "max": 1270.98193359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7058920050672404, "min": 1.8205812151839094, "max": 3.8995645465212387, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1582.4158861637115, "min": 223.93148946762085, "max": 2048.2571739554405, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7058920050672404, "min": 1.8205812151839094, "max": 3.8995645465212387, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1582.4158861637115, "min": 223.93148946762085, "max": 2048.2571739554405, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01475804093588522, "min": 0.012702908283730115, "max": 0.019965946490022663, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02951608187177044, "min": 0.02540581656746023, "max": 0.05707495039872204, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04630844717224439, "min": 0.021752798836678265, "max": 0.055333537277248164, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09261689434448878, "min": 0.04350559767335653, "max": 0.1660006118317445, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.284098572000006e-06, "min": 4.284098572000006e-06, "max": 0.00029535225154925, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.568197144000011e-06, "min": 8.568197144000011e-06, "max": 0.0008442384185871998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10142799999999999, "min": 0.10142799999999999, "max": 0.19845075000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20285599999999998, "min": 0.20285599999999998, "max": 0.5814128, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.125720000000007e-05, "min": 8.125720000000007e-05, "max": 0.004922692425, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016251440000000013, "min": 0.00016251440000000013, "max": 0.01407249872, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712935510", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712938028" }, "total": 2518.614140996, "count": 1, "self": 0.490246489999663, "children": { "run_training.setup": { "total": 0.079965047000087, "count": 1, "self": 0.079965047000087 }, "TrainerController.start_learning": { "total": 2518.043929459, "count": 1, "self": 4.736461768050958, "children": { "TrainerController._reset_env": { "total": 3.6065711310000097, "count": 1, "self": 3.6065711310000097 }, "TrainerController.advance": { "total": 2509.575236726949, "count": 231615, "self": 5.106056732071011, "children": { "env_step": { "total": 2020.1795056149867, "count": 231615, "self": 1675.1013307709989, "children": { "SubprocessEnvManager._take_step": { "total": 342.01185488399506, "count": 231615, "self": 17.686242178860994, "children": { "TorchPolicy.evaluate": { "total": 324.32561270513406, "count": 223122, "self": 324.32561270513406 } } }, "workers": { "total": 3.066319959992825, "count": 231615, "self": 0.0, "children": { "worker_root": { "total": 2510.46826928891, "count": 231615, "is_parallel": true, "self": 1159.8951966739178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011540619999550472, "count": 1, "is_parallel": true, "self": 0.000345359999869288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008087020000857592, "count": 2, "is_parallel": true, "self": 0.0008087020000857592 } } }, "UnityEnvironment.step": { "total": 0.03252037400000063, "count": 1, "is_parallel": true, "self": 0.0004971789999217435, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019566299999951298, "count": 1, "is_parallel": true, "self": 0.00019566299999951298 }, "communicator.exchange": { "total": 0.03094906900003025, "count": 1, "is_parallel": true, "self": 0.03094906900003025 }, "steps_from_proto": { "total": 0.0008784630000491234, "count": 1, "is_parallel": true, "self": 0.00024146200007635343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006370009999727699, "count": 2, "is_parallel": true, "self": 0.0006370009999727699 } } } } } } }, "UnityEnvironment.step": { "total": 1350.5730726149923, "count": 231614, "is_parallel": true, "self": 41.829661509044854, "children": { "UnityEnvironment._generate_step_input": { "total": 84.2902664899459, "count": 231614, "is_parallel": true, "self": 84.2902664899459 }, "communicator.exchange": { "total": 1128.5285348680554, "count": 231614, "is_parallel": true, "self": 1128.5285348680554 }, "steps_from_proto": { "total": 95.92460974794596, "count": 231614, "is_parallel": true, "self": 33.82634405093199, "children": { "_process_rank_one_or_two_observation": { "total": 62.09826569701397, "count": 463228, "is_parallel": true, "self": 62.09826569701397 } } } } } } } } } } }, "trainer_advance": { "total": 484.2896743798909, "count": 231615, "self": 7.267422843832605, "children": { "process_trajectory": { "total": 155.410027128058, "count": 231615, "self": 154.04538424105715, "children": { "RLTrainer._checkpoint": { "total": 1.364642887000855, "count": 10, "self": 1.364642887000855 } } }, "_update_policy": { "total": 321.6122244080003, "count": 96, "self": 257.53634478798995, "children": { "TorchPPOOptimizer.update": { "total": 64.07587962001037, "count": 2880, "self": 64.07587962001037 } } } } } } }, "trainer_threads": { "total": 9.530003808322363e-07, "count": 1, "self": 9.530003808322363e-07 }, "TrainerController._save_models": { "total": 0.12565887999971892, "count": 1, "self": 0.0021964699999443837, "children": { "RLTrainer._checkpoint": { "total": 0.12346240999977454, "count": 1, "self": 0.12346240999977454 } } } } } } }