{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4132167100906372, "min": 1.4132167100906372, "max": 1.4300708770751953, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71864.8984375, "min": 69192.796875, "max": 77605.7734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 109.4780701754386, "min": 89.16847826086956, "max": 416.94166666666666, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49922.0, "min": 48875.0, "max": 50113.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999661.0, "min": 49483.0, "max": 1999661.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999661.0, "min": 49483.0, "max": 1999661.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4142632484436035, "min": 0.08606883138418198, "max": 2.4608898162841797, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1100.904052734375, "min": 10.242191314697266, "max": 1358.4111328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.749983021956787, "min": 1.7626525043439465, "max": 3.9458796507206517, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1709.9922580122948, "min": 209.75564801692963, "max": 2178.1255671977997, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.749983021956787, "min": 1.7626525043439465, "max": 3.9458796507206517, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1709.9922580122948, "min": 209.75564801692963, "max": 2178.1255671977997, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01632592746639906, "min": 0.013402297048499651, "max": 0.020515102967692656, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04897778239919717, "min": 0.027782673988258465, "max": 0.060220473752512285, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.044243268378906776, "min": 0.02231529333318273, "max": 0.057032472060786356, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13272980513672034, "min": 0.04463058666636546, "max": 0.17109741618235907, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6380487873500023e-06, "min": 3.6380487873500023e-06, "max": 0.000295347526550825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0914146362050007e-05, "min": 1.0914146362050007e-05, "max": 0.00084407356864215, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121265000000002, "min": 0.10121265000000002, "max": 0.1984491750000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30363795000000005, "min": 0.2076137, "max": 0.5813578500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.051123500000003e-05, "min": 7.051123500000003e-05, "max": 0.0049226138325000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021153370500000008, "min": 0.00021153370500000008, "max": 0.014069756715, "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": "1696425448", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1696427940" }, "total": 2492.2890368, "count": 1, "self": 0.7893100760002199, "children": { "run_training.setup": { "total": 0.0447625329999255, "count": 1, "self": 0.0447625329999255 }, "TrainerController.start_learning": { "total": 2491.454964191, "count": 1, "self": 4.3389709830325955, "children": { "TrainerController._reset_env": { "total": 4.231004878000022, "count": 1, "self": 4.231004878000022 }, "TrainerController.advance": { "total": 2482.6899685209673, "count": 231790, "self": 4.52067789076591, "children": { "env_step": { "total": 1908.9845147691117, "count": 231790, "self": 1618.6431270570397, "children": { "SubprocessEnvManager._take_step": { "total": 287.4028726890407, "count": 231790, "self": 16.854893354965043, "children": { "TorchPolicy.evaluate": { "total": 270.54797933407565, "count": 223007, "self": 270.54797933407565 } } }, "workers": { "total": 2.9385150230313, "count": 231790, "self": 0.0, "children": { "worker_root": { "total": 2483.6672222081247, "count": 231790, "is_parallel": true, "self": 1162.4512729810408, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008943859999135384, "count": 1, "is_parallel": true, "self": 0.0002497049998737566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006446810000397818, "count": 2, "is_parallel": true, "self": 0.0006446810000397818 } } }, "UnityEnvironment.step": { "total": 0.05081974999995964, "count": 1, "is_parallel": true, "self": 0.00039149400004134804, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022596999997404055, "count": 1, "is_parallel": true, "self": 0.00022596999997404055 }, "communicator.exchange": { "total": 0.049412609000000884, "count": 1, "is_parallel": true, "self": 0.049412609000000884 }, "steps_from_proto": { "total": 0.0007896769999433673, "count": 1, "is_parallel": true, "self": 0.00021251599991956027, "children": { "_process_rank_one_or_two_observation": { "total": 0.000577161000023807, "count": 2, "is_parallel": true, "self": 0.000577161000023807 } } } } } } }, "UnityEnvironment.step": { "total": 1321.215949227084, "count": 231789, "is_parallel": true, "self": 40.400183976097196, "children": { "UnityEnvironment._generate_step_input": { "total": 83.07252429006019, "count": 231789, "is_parallel": true, "self": 83.07252429006019 }, "communicator.exchange": { "total": 1097.1713846329808, "count": 231789, "is_parallel": true, "self": 1097.1713846329808 }, "steps_from_proto": { "total": 100.57185632794574, "count": 231789, "is_parallel": true, "self": 35.64209524900298, "children": { "_process_rank_one_or_two_observation": { "total": 64.92976107894276, "count": 463578, "is_parallel": true, "self": 64.92976107894276 } } } } } } } } } } }, "trainer_advance": { "total": 569.1847758610897, "count": 231790, "self": 6.666901651033413, "children": { "process_trajectory": { "total": 138.26291779605276, "count": 231790, "self": 136.6784691770522, "children": { "RLTrainer._checkpoint": { "total": 1.5844486190005682, "count": 10, "self": 1.5844486190005682 } } }, "_update_policy": { "total": 424.2549564140036, "count": 97, "self": 362.78019029901384, "children": { "TorchPPOOptimizer.update": { "total": 61.474766114989734, "count": 2910, "self": 61.474766114989734 } } } } } } }, "trainer_threads": { "total": 1.3499998203769792e-06, "count": 1, "self": 1.3499998203769792e-06 }, "TrainerController._save_models": { "total": 0.195018459000039, "count": 1, "self": 0.00283455499993579, "children": { "RLTrainer._checkpoint": { "total": 0.1921839040001032, "count": 1, "self": 0.1921839040001032 } } } } } } }