{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4059500694274902, "min": 1.4059500694274902, "max": 1.4280493259429932, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71229.6484375, "min": 68308.390625, "max": 76338.2265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.3577817531306, "min": 78.60987261146497, "max": 390.2421875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49392.0, "min": 48988.0, "max": 50208.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999910.0, "min": 49849.0, "max": 1999910.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999910.0, "min": 49849.0, "max": 1999910.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3775813579559326, "min": 0.06551811099052429, "max": 2.5020713806152344, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1329.0679931640625, "min": 8.320799827575684, "max": 1547.010498046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5326443074640945, "min": 1.5855354227888303, "max": 3.9781964300200343, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1974.748167872429, "min": 201.36299869418144, "max": 2422.5732063651085, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5326443074640945, "min": 1.5855354227888303, "max": 3.9781964300200343, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1974.748167872429, "min": 201.36299869418144, "max": 2422.5732063651085, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017488074651434243, "min": 0.013700645364103063, "max": 0.021943280301153813, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052464223954302724, "min": 0.027401290728206126, "max": 0.05688962720450945, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05667212170859178, "min": 0.02343122838065028, "max": 0.06405349324146907, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17001636512577534, "min": 0.04686245676130056, "max": 0.18048840512832004, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6940987686666756e-06, "min": 3.6940987686666756e-06, "max": 0.00029533950155349994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1082296306000027e-05, "min": 1.1082296306000027e-05, "max": 0.0008442507185831001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123133333333333, "min": 0.10123133333333333, "max": 0.19844649999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30369399999999996, "min": 0.20759295, "max": 0.5814169, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.144353333333348e-05, "min": 7.144353333333348e-05, "max": 0.004922480350000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021433060000000046, "min": 0.00021433060000000046, "max": 0.01407270331, "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": "1687009429", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1687011961" }, "total": 2531.839191976, "count": 1, "self": 0.4353196689999095, "children": { "run_training.setup": { "total": 0.04145838100009769, "count": 1, "self": 0.04145838100009769 }, "TrainerController.start_learning": { "total": 2531.362413926, "count": 1, "self": 4.5883275900273475, "children": { "TrainerController._reset_env": { "total": 4.048572219999983, "count": 1, "self": 4.048572219999983 }, "TrainerController.advance": { "total": 2522.6017757359728, "count": 232496, "self": 4.9625754911717195, "children": { "env_step": { "total": 1982.943243689899, "count": 232496, "self": 1674.5339906808886, "children": { "SubprocessEnvManager._take_step": { "total": 305.3997638239729, "count": 232496, "self": 17.770256708849388, "children": { "TorchPolicy.evaluate": { "total": 287.6295071151235, "count": 223064, "self": 287.6295071151235 } } }, "workers": { "total": 3.0094891850374097, "count": 232496, "self": 0.0, "children": { "worker_root": { "total": 2523.172864013907, "count": 232496, "is_parallel": true, "self": 1157.4885469948947, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011855120000063835, "count": 1, "is_parallel": true, "self": 0.00039558999992550525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007899220000808782, "count": 2, "is_parallel": true, "self": 0.0007899220000808782 } } }, "UnityEnvironment.step": { "total": 0.030262080000056812, "count": 1, "is_parallel": true, "self": 0.0003419160001385535, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023196399990865757, "count": 1, "is_parallel": true, "self": 0.00023196399990865757 }, "communicator.exchange": { "total": 0.02897258600000896, "count": 1, "is_parallel": true, "self": 0.02897258600000896 }, "steps_from_proto": { "total": 0.0007156140000006417, "count": 1, "is_parallel": true, "self": 0.00021708399992803606, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004985300000726056, "count": 2, "is_parallel": true, "self": 0.0004985300000726056 } } } } } } }, "UnityEnvironment.step": { "total": 1365.6843170190125, "count": 232495, "is_parallel": true, "self": 40.26039725695637, "children": { "UnityEnvironment._generate_step_input": { "total": 86.38681407899878, "count": 232495, "is_parallel": true, "self": 86.38681407899878 }, "communicator.exchange": { "total": 1139.9383777060623, "count": 232495, "is_parallel": true, "self": 1139.9383777060623 }, "steps_from_proto": { "total": 99.09872797699495, "count": 232495, "is_parallel": true, "self": 37.655761536924615, "children": { "_process_rank_one_or_two_observation": { "total": 61.442966440070336, "count": 464990, "is_parallel": true, "self": 61.442966440070336 } } } } } } } } } } }, "trainer_advance": { "total": 534.6959565549023, "count": 232496, "self": 6.944176132851453, "children": { "process_trajectory": { "total": 144.20137930005217, "count": 232496, "self": 142.79475196805197, "children": { "RLTrainer._checkpoint": { "total": 1.4066273320001983, "count": 10, "self": 1.4066273320001983 } } }, "_update_policy": { "total": 383.5504011219987, "count": 97, "self": 323.4039994229938, "children": { "TorchPPOOptimizer.update": { "total": 60.146401699004855, "count": 2910, "self": 60.146401699004855 } } } } } } }, "trainer_threads": { "total": 1.2129999049648177e-06, "count": 1, "self": 1.2129999049648177e-06 }, "TrainerController._save_models": { "total": 0.12373716699994475, "count": 1, "self": 0.0020136479997745482, "children": { "RLTrainer._checkpoint": { "total": 0.1217235190001702, "count": 1, "self": 0.1217235190001702 } } } } } } }