{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.400712251663208, "min": 1.400712251663208, "max": 1.4262564182281494, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72296.359375, "min": 68287.8203125, "max": 75635.09375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.9567474048443, "min": 81.70082644628098, "max": 418.43333333333334, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49683.0, "min": 49079.0, "max": 50212.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999482.0, "min": 49791.0, "max": 1999482.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999482.0, "min": 49791.0, "max": 1999482.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.498159885406494, "min": 0.057976722717285156, "max": 2.54156231880188, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1441.438232421875, "min": 6.899230003356934, "max": 1482.017822265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8516958654443356, "min": 1.9082953360150843, "max": 4.005832489875574, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2222.4285143613815, "min": 227.08714498579502, "max": 2355.900084376335, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8516958654443356, "min": 1.9082953360150843, "max": 4.005832489875574, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2222.4285143613815, "min": 227.08714498579502, "max": 2355.900084376335, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01624030969332024, "min": 0.014241045533465998, "max": 0.020673415615359167, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048720929079960715, "min": 0.028482091066931996, "max": 0.057153422935516576, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05013327163954576, "min": 0.022063245779524246, "max": 0.06230598147958517, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15039981491863727, "min": 0.04412649155904849, "max": 0.18047604163487752, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.280848906416666e-06, "min": 3.280848906416666e-06, "max": 0.00029530860156379995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.842546719249997e-06, "min": 9.842546719249997e-06, "max": 0.0008440636686454499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109358333333333, "min": 0.10109358333333333, "max": 0.19843620000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30328075, "min": 0.20731855000000005, "max": 0.5813545500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.456980833333333e-05, "min": 6.456980833333333e-05, "max": 0.004921966380000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019370942499999998, "min": 0.00019370942499999998, "max": 0.014069592045000003, "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": "1675733780", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1675736180" }, "total": 2400.565640895, "count": 1, "self": 0.3899495059995388, "children": { "run_training.setup": { "total": 0.10976066299997456, "count": 1, "self": 0.10976066299997456 }, "TrainerController.start_learning": { "total": 2400.0659307260003, "count": 1, "self": 4.175171223030702, "children": { "TrainerController._reset_env": { "total": 10.024992075, "count": 1, "self": 10.024992075 }, "TrainerController.advance": { "total": 2385.7538938599696, "count": 232527, "self": 4.71021221901583, "children": { "env_step": { "total": 1841.3778471639396, "count": 232527, "self": 1532.5728497348975, "children": { "SubprocessEnvManager._take_step": { "total": 306.01968539704416, "count": 232527, "self": 15.702042016048836, "children": { "TorchPolicy.evaluate": { "total": 290.3176433809953, "count": 223032, "self": 71.38208436300363, "children": { "TorchPolicy.sample_actions": { "total": 218.9355590179917, "count": 223032, "self": 218.9355590179917 } } } } }, "workers": { "total": 2.785312031997819, "count": 232527, "self": 0.0, "children": { "worker_root": { "total": 2392.028919055005, "count": 232527, "is_parallel": true, "self": 1151.0233363959442, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002154598000004171, "count": 1, "is_parallel": true, "self": 0.0003417460000605388, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018128519999436321, "count": 2, "is_parallel": true, "self": 0.0018128519999436321 } } }, "UnityEnvironment.step": { "total": 0.04259456599999112, "count": 1, "is_parallel": true, "self": 0.0003019189999804439, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002243289999910303, "count": 1, "is_parallel": true, "self": 0.0002243289999910303 }, "communicator.exchange": { "total": 0.04137846700001546, "count": 1, "is_parallel": true, "self": 0.04137846700001546 }, "steps_from_proto": { "total": 0.0006898510000041824, "count": 1, "is_parallel": true, "self": 0.00022511999998187093, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004647310000223115, "count": 2, "is_parallel": true, "self": 0.0004647310000223115 } } } } } } }, "UnityEnvironment.step": { "total": 1241.005582659061, "count": 232526, "is_parallel": true, "self": 37.24662712098325, "children": { "UnityEnvironment._generate_step_input": { "total": 77.98616181006042, "count": 232526, "is_parallel": true, "self": 77.98616181006042 }, "communicator.exchange": { "total": 1036.5008146980545, "count": 232526, "is_parallel": true, "self": 1036.5008146980545 }, "steps_from_proto": { "total": 89.27197902996284, "count": 232526, "is_parallel": true, "self": 36.20272963201489, "children": { "_process_rank_one_or_two_observation": { "total": 53.06924939794794, "count": 465052, "is_parallel": true, "self": 53.06924939794794 } } } } } } } } } } }, "trainer_advance": { "total": 539.665834477014, "count": 232527, "self": 6.499163281896017, "children": { "process_trajectory": { "total": 166.22241584811752, "count": 232527, "self": 165.04608407511682, "children": { "RLTrainer._checkpoint": { "total": 1.1763317730006975, "count": 10, "self": 1.1763317730006975 } } }, "_update_policy": { "total": 366.94425534700036, "count": 97, "self": 309.4187604749987, "children": { "TorchPPOOptimizer.update": { "total": 57.52549487200167, "count": 2910, "self": 57.52549487200167 } } } } } } }, "trainer_threads": { "total": 9.860000318440143e-07, "count": 1, "self": 9.860000318440143e-07 }, "TrainerController._save_models": { "total": 0.11187258200016004, "count": 1, "self": 0.0025024100000337057, "children": { "RLTrainer._checkpoint": { "total": 0.10937017200012633, "count": 1, "self": 0.10937017200012633 } } } } } } }