{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4224189519882202, "min": 1.4185680150985718, "max": 1.4224189519882202, "count": 3 }, "Huggy.Policy.Entropy.sum": { "value": 69812.3203125, "min": 69812.3203125, "max": 76321.796875, "count": 3 }, "Huggy.Environment.EpisodeLength.mean": { "value": 278.1564245810056, "min": 278.1564245810056, "max": 370.5037037037037, "count": 3 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49790.0, "min": 49746.0, "max": 50018.0, "count": 3 }, "Huggy.Step.mean": { "value": 149821.0, "min": 49645.0, "max": 149821.0, "count": 3 }, "Huggy.Step.sum": { "value": 149821.0, "min": 49645.0, "max": 149821.0, "count": 3 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 0.547375500202179, "min": 0.03653587028384209, "max": 0.547375500202179, "count": 3 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 97.98020935058594, "min": 4.895806789398193, "max": 97.98020935058594, "count": 3 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.098127110710357, "min": 1.7057722660142984, "max": 3.098127110710357, "count": 3 }, "Huggy.Environment.CumulativeReward.sum": { "value": 554.5647528171539, "min": 228.57348364591599, "max": 554.5647528171539, "count": 3 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.098127110710357, "min": 1.7057722660142984, "max": 3.098127110710357, "count": 3 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 554.5647528171539, "min": 228.57348364591599, "max": 554.5647528171539, "count": 3 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018389357809792273, "min": 0.014864528479544486, "max": 0.01866796039539622, "count": 3 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.055168073429376824, "min": 0.02972905695908897, "max": 0.055168073429376824, "count": 3 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.02478655661559767, "min": 0.02383091676359375, "max": 0.031091275252401827, "count": 3 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.07435966984679301, "min": 0.0476618335271875, "max": 0.07435966984679301, "count": 3 }, "Huggy.Policy.LearningRate.mean": { "value": 0.0002814594561801834, "min": 0.0002814594561801834, "max": 0.0002953760265413249, "count": 3 }, "Huggy.Policy.LearningRate.sum": { "value": 0.0008443783685405501, "min": 0.0005784208571930498, "max": 0.0008443783685405501, "count": 3 }, "Huggy.Policy.Epsilon.mean": { "value": 0.19381981666666662, "min": 0.19381981666666662, "max": 0.19845867500000008, "count": 3 }, "Huggy.Policy.Epsilon.sum": { "value": 0.5814594499999999, "min": 0.39280695, "max": 0.5814594499999999, "count": 3 }, "Huggy.Policy.Beta.mean": { "value": 0.004691608851666667, "min": 0.004691608851666667, "max": 0.0049230878825000015, "count": 3 }, "Huggy.Policy.Beta.sum": { "value": 0.014074826555, "min": 0.009641066805000001, "max": 0.014074826555, "count": 3 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718113598", "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": "1718113948" }, "total": 350.070629682, "count": 1, "self": 0.5694031900000027, "children": { "run_training.setup": { "total": 0.0799166360000072, "count": 1, "self": 0.0799166360000072 }, "TrainerController.start_learning": { "total": 349.421309856, "count": 1, "self": 0.6370922930042298, "children": { "TrainerController._reset_env": { "total": 3.710875890000011, "count": 1, "self": 3.710875890000011 }, "TrainerController.advance": { "total": 344.69924584299554, "count": 18059, "self": 0.6746092930027316, "children": { "env_step": { "total": 234.78850028700697, "count": 18059, "self": 195.53889762200845, "children": { "SubprocessEnvManager._take_step": { "total": 38.83199416799664, "count": 18059, "self": 2.4275863289930157, "children": { "TorchPolicy.evaluate": { "total": 36.404407839003625, "count": 17831, "self": 36.404407839003625 } } }, "workers": { "total": 0.4176084970018792, "count": 18058, "self": 0.0, "children": { "worker_root": { "total": 348.0416725180023, "count": 18058, "is_parallel": true, "self": 195.0154924990021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004423501000019314, "count": 1, "is_parallel": true, "self": 0.0004571439999381255, "children": { "_process_rank_one_or_two_observation": { "total": 0.003966357000081189, "count": 2, "is_parallel": true, "self": 0.003966357000081189 } } }, "UnityEnvironment.step": { "total": 0.038938804999929744, "count": 1, "is_parallel": true, "self": 0.00054452200004107, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026880099994741613, "count": 1, "is_parallel": true, "self": 0.00026880099994741613 }, "communicator.exchange": { "total": 0.037091329999952904, "count": 1, "is_parallel": true, "self": 0.037091329999952904 }, "steps_from_proto": { "total": 0.001034151999988353, "count": 1, "is_parallel": true, "self": 0.00026089699997555726, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007732550000127958, "count": 2, "is_parallel": true, "self": 0.0007732550000127958 } } } } } } }, "UnityEnvironment.step": { "total": 153.0261800190002, "count": 18057, "is_parallel": true, "self": 5.090068617999577, "children": { "UnityEnvironment._generate_step_input": { "total": 9.207936113989149, "count": 18057, "is_parallel": true, "self": 9.207936113989149 }, "communicator.exchange": { "total": 127.92304048500569, "count": 18057, "is_parallel": true, "self": 127.92304048500569 }, "steps_from_proto": { "total": 10.805134802005796, "count": 18057, "is_parallel": true, "self": 3.5029096829991886, "children": { "_process_rank_one_or_two_observation": { "total": 7.302225119006607, "count": 36114, "is_parallel": true, "self": 7.302225119006607 } } } } } } } } } } }, "trainer_advance": { "total": 109.23613626298584, "count": 18058, "self": 0.9935924079796905, "children": { "process_trajectory": { "total": 15.242047851006191, "count": 18058, "self": 15.242047851006191 }, "_update_policy": { "total": 93.00049600399996, "count": 7, "self": 24.526719303000846, "children": { "TorchPPOOptimizer.update": { "total": 68.47377670099911, "count": 210, "self": 68.47377670099911 } } } } } } }, "trainer_threads": { "total": 2.1230000584182562e-06, "count": 1, "self": 2.1230000584182562e-06 }, "TrainerController._save_models": { "total": 0.37409370700015643, "count": 1, "self": 0.0039052860001902445, "children": { "RLTrainer._checkpoint": { "total": 0.3701884209999662, "count": 1, "self": 0.3701884209999662 } } } } } } }