{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4057258367538452, "min": 1.4057258367538452, "max": 1.4278279542922974, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70329.8671875, "min": 68906.28125, "max": 76974.921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.18858954041204, "min": 78.18858954041204, "max": 382.5496183206107, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49337.0, "min": 48957.0, "max": 50114.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999855.0, "min": 49772.0, "max": 1999855.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999855.0, "min": 49772.0, "max": 1999855.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.463425874710083, "min": 0.029370170086622238, "max": 2.5329480171203613, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1554.4217529296875, "min": 3.818122148513794, "max": 1554.4217529296875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7500239050520583, "min": 1.8426551637168114, "max": 4.0213838674064375, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2366.2650840878487, "min": 239.54517128318548, "max": 2369.8829966187477, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7500239050520583, "min": 1.8426551637168114, "max": 4.0213838674064375, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2366.2650840878487, "min": 239.54517128318548, "max": 2369.8829966187477, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01668918830222942, "min": 0.012822001694197145, "max": 0.020666355073141553, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050067564906688254, "min": 0.02564400338839429, "max": 0.05946281325304881, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06229962747957971, "min": 0.024011620972305536, "max": 0.06525156032294034, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18689888243873914, "min": 0.04802324194461107, "max": 0.18689888243873914, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4135488621833407e-06, "min": 3.4135488621833407e-06, "max": 0.00029534572655142495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0240646586550022e-05, "min": 1.0240646586550022e-05, "max": 0.00084421606859465, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011378166666667, "min": 0.1011378166666667, "max": 0.19844857500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034134500000001, "min": 0.20740824999999996, "max": 0.58140535, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.67770516666668e-05, "min": 6.67770516666668e-05, "max": 0.004922583892500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002003311550000004, "min": 0.0002003311550000004, "max": 0.014072126965000003, "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": "1709498879", "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": "1709501243" }, "total": 2364.185880722, "count": 1, "self": 0.4427314010004011, "children": { "run_training.setup": { "total": 0.05877380499998708, "count": 1, "self": 0.05877380499998708 }, "TrainerController.start_learning": { "total": 2363.684375516, "count": 1, "self": 4.518385023002793, "children": { "TrainerController._reset_env": { "total": 3.193213042000025, "count": 1, "self": 3.193213042000025 }, "TrainerController.advance": { "total": 2355.8547685739964, "count": 232836, "self": 4.615798684050333, "children": { "env_step": { "total": 1858.1569159750447, "count": 232836, "self": 1536.0136272350765, "children": { "SubprocessEnvManager._take_step": { "total": 319.40578344290884, "count": 232836, "self": 16.594101673921045, "children": { "TorchPolicy.evaluate": { "total": 302.8116817689878, "count": 222952, "self": 302.8116817689878 } } }, "workers": { "total": 2.7375052970593288, "count": 232836, "self": 0.0, "children": { "worker_root": { "total": 2356.6139356250424, "count": 232836, "is_parallel": true, "self": 1102.1109145120745, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010729980000405703, "count": 1, "is_parallel": true, "self": 0.00029094600006374094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007820519999768294, "count": 2, "is_parallel": true, "self": 0.0007820519999768294 } } }, "UnityEnvironment.step": { "total": 0.02928862199996729, "count": 1, "is_parallel": true, "self": 0.00037183799997819733, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000222122999957719, "count": 1, "is_parallel": true, "self": 0.000222122999957719 }, "communicator.exchange": { "total": 0.027945655000053193, "count": 1, "is_parallel": true, "self": 0.027945655000053193 }, "steps_from_proto": { "total": 0.0007490059999781806, "count": 1, "is_parallel": true, "self": 0.00019597599998633086, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005530299999918498, "count": 2, "is_parallel": true, "self": 0.0005530299999918498 } } } } } } }, "UnityEnvironment.step": { "total": 1254.5030211129679, "count": 232835, "is_parallel": true, "self": 40.94045029100516, "children": { "UnityEnvironment._generate_step_input": { "total": 81.06136262898167, "count": 232835, "is_parallel": true, "self": 81.06136262898167 }, "communicator.exchange": { "total": 1041.4195510139507, "count": 232835, "is_parallel": true, "self": 1041.4195510139507 }, "steps_from_proto": { "total": 91.08165717903046, "count": 232835, "is_parallel": true, "self": 31.7316068871379, "children": { "_process_rank_one_or_two_observation": { "total": 59.35005029189256, "count": 465670, "is_parallel": true, "self": 59.35005029189256 } } } } } } } } } } }, "trainer_advance": { "total": 493.08205391490105, "count": 232836, "self": 6.70158543982302, "children": { "process_trajectory": { "total": 150.88918763907748, "count": 232836, "self": 149.7353009760776, "children": { "RLTrainer._checkpoint": { "total": 1.1538866629998665, "count": 10, "self": 1.1538866629998665 } } }, "_update_policy": { "total": 335.49128083600056, "count": 97, "self": 270.02647791900176, "children": { "TorchPPOOptimizer.update": { "total": 65.46480291699879, "count": 2910, "self": 65.46480291699879 } } } } } } }, "trainer_threads": { "total": 8.760002856433857e-07, "count": 1, "self": 8.760002856433857e-07 }, "TrainerController._save_models": { "total": 0.11800800100036213, "count": 1, "self": 0.002171148000343237, "children": { "RLTrainer._checkpoint": { "total": 0.11583685300001889, "count": 1, "self": 0.11583685300001889 } } } } } } }