{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405411720275879, "min": 1.405411720275879, "max": 1.4318861961364746, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72011.890625, "min": 68791.96875, "max": 77639.625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 112.210407239819, "min": 101.67148760330579, "max": 423.5546218487395, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49597.0, "min": 48924.0, "max": 50403.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999952.0, "min": 49857.0, "max": 1999952.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999952.0, "min": 49857.0, "max": 1999952.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.288228988647461, "min": -0.05898061767220497, "max": 2.371009111404419, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1011.397216796875, "min": -6.959712982177734, "max": 1122.308837890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.481129947156388, "min": 1.7820990666494532, "max": 3.8842273863879115, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1538.6594366431236, "min": 210.28768986463547, "max": 1723.72651720047, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.481129947156388, "min": 1.7820990666494532, "max": 3.8842273863879115, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1538.6594366431236, "min": 210.28768986463547, "max": 1723.72651720047, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017952424590475857, "min": 0.013406705137701161, "max": 0.021753117905852076, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.035904849180951715, "min": 0.026813410275402322, "max": 0.061713808709949566, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04845151311407486, "min": 0.021252846407393614, "max": 0.06842205077409744, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09690302622814972, "min": 0.04250569281478723, "max": 0.20384134612977506, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.912998695699991e-06, "min": 3.912998695699991e-06, "max": 0.000295340626553125, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 7.825997391399982e-06, "min": 7.825997391399982e-06, "max": 0.0008441722686092499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1013043, "min": 0.1013043, "max": 0.19844687500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2026086, "min": 0.2026086, "max": 0.5813907500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.508456999999989e-05, "min": 7.508456999999989e-05, "max": 0.0049224990625, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00015016913999999978, "min": 0.00015016913999999978, "max": 0.014071398425000003, "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": "1672172600", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1672174795" }, "total": 2194.805721719, "count": 1, "self": 0.3920503569997891, "children": { "run_training.setup": { "total": 0.1284058059999893, "count": 1, "self": 0.1284058059999893 }, "TrainerController.start_learning": { "total": 2194.285265556, "count": 1, "self": 3.7711830069774805, "children": { "TrainerController._reset_env": { "total": 8.561112200000025, "count": 1, "self": 8.561112200000025 }, "TrainerController.advance": { "total": 2181.8313167480223, "count": 230946, "self": 4.1609159069748785, "children": { "env_step": { "total": 1719.9729042650097, "count": 230946, "self": 1440.9575609100905, "children": { "SubprocessEnvManager._take_step": { "total": 276.4637706829729, "count": 230946, "self": 14.174676477982018, "children": { "TorchPolicy.evaluate": { "total": 262.2890942049909, "count": 223070, "self": 65.9387494720666, "children": { "TorchPolicy.sample_actions": { "total": 196.35034473292427, "count": 223070, "self": 196.35034473292427 } } } } }, "workers": { "total": 2.551572671946303, "count": 230946, "self": 0.0, "children": { "worker_root": { "total": 2186.627082882973, "count": 230946, "is_parallel": true, "self": 1001.1281734879376, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002227395999966575, "count": 1, "is_parallel": true, "self": 0.0003645439999786504, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018628519999879245, "count": 2, "is_parallel": true, "self": 0.0018628519999879245 } } }, "UnityEnvironment.step": { "total": 0.02664764200000036, "count": 1, "is_parallel": true, "self": 0.00029310700000451106, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017173100002310093, "count": 1, "is_parallel": true, "self": 0.00017173100002310093 }, "communicator.exchange": { "total": 0.025483485999984623, "count": 1, "is_parallel": true, "self": 0.025483485999984623 }, "steps_from_proto": { "total": 0.0006993179999881249, "count": 1, "is_parallel": true, "self": 0.00025564699996039053, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004436710000277344, "count": 2, "is_parallel": true, "self": 0.0004436710000277344 } } } } } } }, "UnityEnvironment.step": { "total": 1185.4989093950353, "count": 230945, "is_parallel": true, "self": 33.85120677004852, "children": { "UnityEnvironment._generate_step_input": { "total": 73.89714934805227, "count": 230945, "is_parallel": true, "self": 73.89714934805227 }, "communicator.exchange": { "total": 985.8102032129173, "count": 230945, "is_parallel": true, "self": 985.8102032129173 }, "steps_from_proto": { "total": 91.94035006401737, "count": 230945, "is_parallel": true, "self": 37.52395877402478, "children": { "_process_rank_one_or_two_observation": { "total": 54.41639128999259, "count": 461890, "is_parallel": true, "self": 54.41639128999259 } } } } } } } } } } }, "trainer_advance": { "total": 457.6974965760378, "count": 230946, "self": 6.26221248490765, "children": { "process_trajectory": { "total": 140.8108965861298, "count": 230946, "self": 139.64107053912943, "children": { "RLTrainer._checkpoint": { "total": 1.169826047000356, "count": 10, "self": 1.169826047000356 } } }, "_update_policy": { "total": 310.62438750500036, "count": 96, "self": 257.81391564400235, "children": { "TorchPPOOptimizer.update": { "total": 52.81047186099801, "count": 2880, "self": 52.81047186099801 } } } } } } }, "trainer_threads": { "total": 7.960002221807372e-07, "count": 1, "self": 7.960002221807372e-07 }, "TrainerController._save_models": { "total": 0.12165280499993969, "count": 1, "self": 0.0025814989999162208, "children": { "RLTrainer._checkpoint": { "total": 0.11907130600002347, "count": 1, "self": 0.11907130600002347 } } } } } } }