{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408005714416504, "min": 1.408005714416504, "max": 1.4311772584915161, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68303.765625, "min": 68303.765625, "max": 77754.40625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.07786885245902, "min": 96.29423076923077, "max": 396.93650793650795, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48838.0, "min": 48838.0, "max": 50266.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999976.0, "min": 49691.0, "max": 1999976.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999976.0, "min": 49691.0, "max": 1999976.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.397092580795288, "min": 0.1799723356962204, "max": 2.4211385250091553, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1169.7811279296875, "min": 22.49654197692871, "max": 1230.152099609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.726319296682467, "min": 1.8794116578102111, "max": 3.8541886832703045, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1818.443816781044, "min": 234.9264572262764, "max": 1921.0930666327477, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.726319296682467, "min": 1.8794116578102111, "max": 3.8541886832703045, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1818.443816781044, "min": 234.9264572262764, "max": 1921.0930666327477, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016848336476444577, "min": 0.013100478733839635, "max": 0.019888670139092332, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03369667295288915, "min": 0.0283447386589008, "max": 0.059666010417276996, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04902337354918321, "min": 0.021282983912775916, "max": 0.057648326456546786, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09804674709836642, "min": 0.04256596782555183, "max": 0.16607637790342172, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.602323465924987e-06, "min": 4.602323465924987e-06, "max": 0.0002953713015429, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.204646931849974e-06, "min": 9.204646931849974e-06, "max": 0.00084415576861475, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101534075, "min": 0.101534075, "max": 0.1984571, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20306815, "min": 0.20306815, "max": 0.5813852500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.655034249999981e-05, "min": 8.655034249999981e-05, "max": 0.0049230092900000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017310068499999963, "min": 0.00017310068499999963, "max": 0.014071123974999999, "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": "1689502315", "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": "1689504891" }, "total": 2576.136128309, "count": 1, "self": 0.4903040730005159, "children": { "run_training.setup": { "total": 0.04381412099996851, "count": 1, "self": 0.04381412099996851 }, "TrainerController.start_learning": { "total": 2575.6020101149998, "count": 1, "self": 4.95383159794892, "children": { "TrainerController._reset_env": { "total": 5.113575024000056, "count": 1, "self": 5.113575024000056 }, "TrainerController.advance": { "total": 2565.404021343051, "count": 231147, "self": 4.9067443311109855, "children": { "env_step": { "total": 1992.0653724779606, "count": 231147, "self": 1683.612728891045, "children": { "SubprocessEnvManager._take_step": { "total": 305.41315053199185, "count": 231147, "self": 17.762970167127833, "children": { "TorchPolicy.evaluate": { "total": 287.650180364864, "count": 222840, "self": 287.650180364864 } } }, "workers": { "total": 3.0394930549238097, "count": 231147, "self": 0.0, "children": { "worker_root": { "total": 2567.465212134966, "count": 231147, "is_parallel": true, "self": 1191.57415336806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009488539999438217, "count": 1, "is_parallel": true, "self": 0.00026361799984897516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006852360000948465, "count": 2, "is_parallel": true, "self": 0.0006852360000948465 } } }, "UnityEnvironment.step": { "total": 0.05017973899998651, "count": 1, "is_parallel": true, "self": 0.00034536299995124864, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002623139999968771, "count": 1, "is_parallel": true, "self": 0.0002623139999968771 }, "communicator.exchange": { "total": 0.04878806199997143, "count": 1, "is_parallel": true, "self": 0.04878806199997143 }, "steps_from_proto": { "total": 0.0007840000000669534, "count": 1, "is_parallel": true, "self": 0.00022481300004528748, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005591870000216659, "count": 2, "is_parallel": true, "self": 0.0005591870000216659 } } } } } } }, "UnityEnvironment.step": { "total": 1375.8910587669059, "count": 231146, "is_parallel": true, "self": 42.84415243890794, "children": { "UnityEnvironment._generate_step_input": { "total": 84.38831256704191, "count": 231146, "is_parallel": true, "self": 84.38831256704191 }, "communicator.exchange": { "total": 1144.842078958984, "count": 231146, "is_parallel": true, "self": 1144.842078958984 }, "steps_from_proto": { "total": 103.81651480197195, "count": 231146, "is_parallel": true, "self": 36.39690147995873, "children": { "_process_rank_one_or_two_observation": { "total": 67.41961332201322, "count": 462292, "is_parallel": true, "self": 67.41961332201322 } } } } } } } } } } }, "trainer_advance": { "total": 568.4319045339796, "count": 231147, "self": 7.163790316975678, "children": { "process_trajectory": { "total": 139.0526748780061, "count": 231147, "self": 137.57514355700653, "children": { "RLTrainer._checkpoint": { "total": 1.4775313209995602, "count": 10, "self": 1.4775313209995602 } } }, "_update_policy": { "total": 422.21543933899784, "count": 96, "self": 360.0581694780079, "children": { "TorchPPOOptimizer.update": { "total": 62.15726986098991, "count": 2880, "self": 62.15726986098991 } } } } } } }, "trainer_threads": { "total": 1.327999598288443e-06, "count": 1, "self": 1.327999598288443e-06 }, "TrainerController._save_models": { "total": 0.13058082199995624, "count": 1, "self": 0.0027426669998931175, "children": { "RLTrainer._checkpoint": { "total": 0.12783815500006313, "count": 1, "self": 0.12783815500006313 } } } } } } }