{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4037331342697144, "min": 1.4037331342697144, "max": 1.427725076675415, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70317.203125, "min": 68959.75, "max": 78278.21875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.89, "min": 90.22262773722628, "max": 387.4651162790698, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49445.0, "min": 49076.0, "max": 50191.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999938.0, "min": 49734.0, "max": 1999938.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999938.0, "min": 49734.0, "max": 1999938.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.374952554702759, "min": 0.06496812403202057, "max": 2.4421584606170654, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1187.476318359375, "min": 8.315919876098633, "max": 1283.68603515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.673716370820999, "min": 1.7477193042868748, "max": 3.858492168821866, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1836.8581854104996, "min": 223.70807094871998, "max": 2028.5384631752968, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.673716370820999, "min": 1.7477193042868748, "max": 3.858492168821866, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1836.8581854104996, "min": 223.70807094871998, "max": 2028.5384631752968, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017672260180309728, "min": 0.014155591032572879, "max": 0.02053834101728474, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05301678054092918, "min": 0.02976001013691227, "max": 0.055887369138751336, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05130157586601045, "min": 0.02264845318471392, "max": 0.059975557650129, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15390472759803137, "min": 0.04529690636942784, "max": 0.17905283806224664, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.324198891966663e-06, "min": 3.324198891966663e-06, "max": 0.000295359076546975, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.972596675899989e-06, "min": 9.972596675899989e-06, "max": 0.0008441557686147499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110803333333333, "min": 0.10110803333333333, "max": 0.198453025, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033241, "min": 0.20735185000000006, "max": 0.58138525, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.529086333333328e-05, "min": 6.529086333333328e-05, "max": 0.004922805947500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019587258999999985, "min": 0.00019587258999999985, "max": 0.014071123975, "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": "1719721538", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719723903" }, "total": 2365.06311279, "count": 1, "self": 0.4356997960003355, "children": { "run_training.setup": { "total": 0.06850610599997253, "count": 1, "self": 0.06850610599997253 }, "TrainerController.start_learning": { "total": 2364.558906888, "count": 1, "self": 4.209201144991312, "children": { "TrainerController._reset_env": { "total": 3.074438013999952, "count": 1, "self": 3.074438013999952 }, "TrainerController.advance": { "total": 2357.161872451008, "count": 231430, "self": 4.627517241071928, "children": { "env_step": { "total": 1871.302361572946, "count": 231430, "self": 1543.599739140026, "children": { "SubprocessEnvManager._take_step": { "total": 324.87325439092785, "count": 231430, "self": 16.182611277889805, "children": { "TorchPolicy.evaluate": { "total": 308.69064311303805, "count": 222922, "self": 308.69064311303805 } } }, "workers": { "total": 2.829368041992211, "count": 231430, "self": 0.0, "children": { "worker_root": { "total": 2357.726987054906, "count": 231430, "is_parallel": true, "self": 1113.300828533007, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008617729999969015, "count": 1, "is_parallel": true, "self": 0.00020658699997966323, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006551860000172383, "count": 2, "is_parallel": true, "self": 0.0006551860000172383 } } }, "UnityEnvironment.step": { "total": 0.028663894999908734, "count": 1, "is_parallel": true, "self": 0.000381161999825963, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019787099995483004, "count": 1, "is_parallel": true, "self": 0.00019787099995483004 }, "communicator.exchange": { "total": 0.027245387000107257, "count": 1, "is_parallel": true, "self": 0.027245387000107257 }, "steps_from_proto": { "total": 0.0008394750000206841, "count": 1, "is_parallel": true, "self": 0.00019720199998118915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006422730000394949, "count": 2, "is_parallel": true, "self": 0.0006422730000394949 } } } } } } }, "UnityEnvironment.step": { "total": 1244.4261585218992, "count": 231429, "is_parallel": true, "self": 38.367670499887254, "children": { "UnityEnvironment._generate_step_input": { "total": 78.29571704701061, "count": 231429, "is_parallel": true, "self": 78.29571704701061 }, "communicator.exchange": { "total": 1040.4560010260552, "count": 231429, "is_parallel": true, "self": 1040.4560010260552 }, "steps_from_proto": { "total": 87.30676994894611, "count": 231429, "is_parallel": true, "self": 30.752341676889046, "children": { "_process_rank_one_or_two_observation": { "total": 56.554428272057066, "count": 462858, "is_parallel": true, "self": 56.554428272057066 } } } } } } } } } } }, "trainer_advance": { "total": 481.23199363699007, "count": 231430, "self": 6.654478223961291, "children": { "process_trajectory": { "total": 147.79140206602722, "count": 231430, "self": 146.4829516840265, "children": { "RLTrainer._checkpoint": { "total": 1.3084503820007285, "count": 10, "self": 1.3084503820007285 } } }, "_update_policy": { "total": 326.78611334700156, "count": 97, "self": 263.240326142003, "children": { "TorchPPOOptimizer.update": { "total": 63.54578720499853, "count": 2910, "self": 63.54578720499853 } } } } } } }, "trainer_threads": { "total": 1.214000349136768e-06, "count": 1, "self": 1.214000349136768e-06 }, "TrainerController._save_models": { "total": 0.1133940640002038, "count": 1, "self": 0.0018780730001708434, "children": { "RLTrainer._checkpoint": { "total": 0.11151599100003295, "count": 1, "self": 0.11151599100003295 } } } } } } }