{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4051601886749268, "min": 1.4051601886749268, "max": 1.4279659986495972, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70807.4296875, "min": 67304.625, "max": 78681.3515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.39766081871345, "min": 96.39766081871345, "max": 405.06451612903226, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49452.0, "min": 48939.0, "max": 50228.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999943.0, "min": 49869.0, "max": 1999943.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999943.0, "min": 49869.0, "max": 1999943.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4020235538482666, "min": 0.13750040531158447, "max": 2.4020235538482666, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1232.238037109375, "min": 16.91254997253418, "max": 1232.238037109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.792737126118026, "min": 1.7804102754689815, "max": 3.8783307232768682, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1945.6741456985474, "min": 218.9904638826847, "max": 1945.6741456985474, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.792737126118026, "min": 1.7804102754689815, "max": 3.8783307232768682, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1945.6741456985474, "min": 218.9904638826847, "max": 1945.6741456985474, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017192138884638553, "min": 0.01331498797420257, "max": 0.02130076438334072, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.034384277769277105, "min": 0.02662997594840514, "max": 0.05913366912670123, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052620048200090724, "min": 0.021938750240951776, "max": 0.05701244932909806, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10524009640018145, "min": 0.04387750048190355, "max": 0.16697687345246476, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.582073472675004e-06, "min": 4.582073472675004e-06, "max": 0.00029536207654597493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.164146945350008e-06, "min": 9.164146945350008e-06, "max": 0.0008440288686570499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10152732500000004, "min": 0.10152732500000004, "max": 0.19845402500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2030546500000001, "min": 0.2030546500000001, "max": 0.5813429499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.62135175000001e-05, "min": 8.62135175000001e-05, "max": 0.004922855847499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001724270350000002, "min": 0.0001724270350000002, "max": 0.014069013205000001, "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": "1712852806", "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": "1712855248" }, "total": 2442.1442690460244, "count": 1, "self": 0.32314701296854764, "children": { "run_training.setup": { "total": 0.06038508005440235, "count": 1, "self": 0.06038508005440235 }, "TrainerController.start_learning": { "total": 2441.7607369530015, "count": 1, "self": 4.789328233571723, "children": { "TrainerController._reset_env": { "total": 1.6124414460500702, "count": 1, "self": 1.6124414460500702 }, "TrainerController.advance": { "total": 2435.2599040223286, "count": 230955, "self": 4.238214854034595, "children": { "env_step": { "total": 2033.3303406008054, "count": 230955, "self": 1684.7883076292928, "children": { "SubprocessEnvManager._take_step": { "total": 345.5045541707659, "count": 230955, "self": 13.6527558285743, "children": { "TorchPolicy.evaluate": { "total": 331.8517983421916, "count": 222954, "self": 331.8517983421916 } } }, "workers": { "total": 3.0374788007466123, "count": 230955, "self": 0.0, "children": { "worker_root": { "total": 2434.0955062659923, "count": 230955, "is_parallel": true, "self": 1056.9958357597934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008380189538002014, "count": 1, "is_parallel": true, "self": 0.00023860891815274954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005994100356474519, "count": 2, "is_parallel": true, "self": 0.0005994100356474519 } } }, "UnityEnvironment.step": { "total": 0.02205382799729705, "count": 1, "is_parallel": true, "self": 0.000385044957511127, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020978599786758423, "count": 1, "is_parallel": true, "self": 0.00020978599786758423 }, "communicator.exchange": { "total": 0.020734571968205273, "count": 1, "is_parallel": true, "self": 0.020734571968205273 }, "steps_from_proto": { "total": 0.0007244250737130642, "count": 1, "is_parallel": true, "self": 0.0002178400754928589, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005065849982202053, "count": 2, "is_parallel": true, "self": 0.0005065849982202053 } } } } } } }, "UnityEnvironment.step": { "total": 1377.099670506199, "count": 230954, "is_parallel": true, "self": 43.636263823951595, "children": { "UnityEnvironment._generate_step_input": { "total": 89.25680337508675, "count": 230954, "is_parallel": true, "self": 89.25680337508675 }, "communicator.exchange": { "total": 1148.094032486435, "count": 230954, "is_parallel": true, "self": 1148.094032486435 }, "steps_from_proto": { "total": 96.11257082072552, "count": 230954, "is_parallel": true, "self": 35.12618116650265, "children": { "_process_rank_one_or_two_observation": { "total": 60.986389654222876, "count": 461908, "is_parallel": true, "self": 60.986389654222876 } } } } } } } } } } }, "trainer_advance": { "total": 397.6913485674886, "count": 230955, "self": 6.721418106346391, "children": { "process_trajectory": { "total": 132.88197737908922, "count": 230955, "self": 131.94903566723224, "children": { "RLTrainer._checkpoint": { "total": 0.9329417118569836, "count": 10, "self": 0.9329417118569836 } } }, "_update_policy": { "total": 258.087953082053, "count": 96, "self": 213.04541358479764, "children": { "TorchPPOOptimizer.update": { "total": 45.04253949725535, "count": 2880, "self": 45.04253949725535 } } } } } } }, "trainer_threads": { "total": 1.0119983926415443e-06, "count": 1, "self": 1.0119983926415443e-06 }, "TrainerController._save_models": { "total": 0.09906223905272782, "count": 1, "self": 0.002148709027096629, "children": { "RLTrainer._checkpoint": { "total": 0.09691353002563119, "count": 1, "self": 0.09691353002563119 } } } } } } }