{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4078136682510376, "min": 1.4078136682510376, "max": 1.4268040657043457, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69391.1328125, "min": 68889.9453125, "max": 77860.234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.17977528089888, "min": 86.33507853403141, "max": 376.85714285714283, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49224.0, "min": 48974.0, "max": 50122.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999944.0, "min": 49813.0, "max": 1999944.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999944.0, "min": 49813.0, "max": 1999944.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.391021251678467, "min": 0.14932088553905487, "max": 2.459251642227173, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1276.8052978515625, "min": 19.710357666015625, "max": 1406.87353515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.575771658161606, "min": 1.8584200887743272, "max": 3.9355171180433697, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1909.4620654582977, "min": 245.31145171821117, "max": 2224.3485311865807, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.575771658161606, "min": 1.8584200887743272, "max": 3.9355171180433697, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1909.4620654582977, "min": 245.31145171821117, "max": 2224.3485311865807, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01899833439221968, "min": 0.014154496433911845, "max": 0.02008026219991734, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05699500317665904, "min": 0.02830899286782369, "max": 0.05699500317665904, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0549429169545571, "min": 0.021842945832759142, "max": 0.06162155705193678, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1648287508636713, "min": 0.043685891665518284, "max": 0.17293203473091126, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.394598868499999e-06, "min": 3.394598868499999e-06, "max": 0.00029535262654912506, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0183796605499998e-05, "min": 1.0183796605499998e-05, "max": 0.0008440708686430501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011315, "min": 0.1011315, "max": 0.19845087499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033945, "min": 0.20743264999999997, "max": 0.5813569499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.646185e-05, "min": 6.646185e-05, "max": 0.004922698662500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019938555, "min": 0.00019938555, "max": 0.014069711805, "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": "1674034854", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.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": "1674037051" }, "total": 2196.268415697, "count": 1, "self": 0.3870397469991076, "children": { "run_training.setup": { "total": 0.09862983000016357, "count": 1, "self": 0.09862983000016357 }, "TrainerController.start_learning": { "total": 2195.7827461200004, "count": 1, "self": 3.840411798972127, "children": { "TrainerController._reset_env": { "total": 9.921792130000085, "count": 1, "self": 9.921792130000085 }, "TrainerController.advance": { "total": 2181.8739903790283, "count": 231950, "self": 4.147655221129753, "children": { "env_step": { "total": 1734.2961435360173, "count": 231950, "self": 1452.3412505761219, "children": { "SubprocessEnvManager._take_step": { "total": 279.3805550538607, "count": 231950, "self": 14.523292083759316, "children": { "TorchPolicy.evaluate": { "total": 264.8572629701014, "count": 222880, "self": 66.02558970604059, "children": { "TorchPolicy.sample_actions": { "total": 198.83167326406078, "count": 222880, "self": 198.83167326406078 } } } } }, "workers": { "total": 2.5743379060347706, "count": 231950, "self": 0.0, "children": { "worker_root": { "total": 2187.7993283899864, "count": 231950, "is_parallel": true, "self": 994.4800989929292, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001999688000069, "count": 1, "is_parallel": true, "self": 0.0003155309998419398, "children": { "_process_rank_one_or_two_observation": { "total": 0.00168415700022706, "count": 2, "is_parallel": true, "self": 0.00168415700022706 } } }, "UnityEnvironment.step": { "total": 0.029407194999976127, "count": 1, "is_parallel": true, "self": 0.00027588199986894324, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020062999988113006, "count": 1, "is_parallel": true, "self": 0.00020062999988113006 }, "communicator.exchange": { "total": 0.028247246000091764, "count": 1, "is_parallel": true, "self": 0.028247246000091764 }, "steps_from_proto": { "total": 0.0006834370001342904, "count": 1, "is_parallel": true, "self": 0.00022417700006371888, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045926000007057155, "count": 2, "is_parallel": true, "self": 0.00045926000007057155 } } } } } } }, "UnityEnvironment.step": { "total": 1193.3192293970571, "count": 231949, "is_parallel": true, "self": 33.87554863486048, "children": { "UnityEnvironment._generate_step_input": { "total": 77.62883001810428, "count": 231949, "is_parallel": true, "self": 77.62883001810428 }, "communicator.exchange": { "total": 989.6991030049835, "count": 231949, "is_parallel": true, "self": 989.6991030049835 }, "steps_from_proto": { "total": 92.11574773910888, "count": 231949, "is_parallel": true, "self": 39.678345030095215, "children": { "_process_rank_one_or_two_observation": { "total": 52.43740270901367, "count": 463898, "is_parallel": true, "self": 52.43740270901367 } } } } } } } } } } }, "trainer_advance": { "total": 443.43019162188125, "count": 231950, "self": 5.844322373878185, "children": { "process_trajectory": { "total": 144.6584765840057, "count": 231950, "self": 143.56948060700552, "children": { "RLTrainer._checkpoint": { "total": 1.0889959770001951, "count": 10, "self": 1.0889959770001951 } } }, "_update_policy": { "total": 292.92739266399735, "count": 97, "self": 241.04878453000174, "children": { "TorchPPOOptimizer.update": { "total": 51.87860813399561, "count": 2910, "self": 51.87860813399561 } } } } } } }, "trainer_threads": { "total": 7.730000106676016e-07, "count": 1, "self": 7.730000106676016e-07 }, "TrainerController._save_models": { "total": 0.14655103899985988, "count": 1, "self": 0.0019946539996453794, "children": { "RLTrainer._checkpoint": { "total": 0.1445563850002145, "count": 1, "self": 0.1445563850002145 } } } } } } }