{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4049279689788818, "min": 1.4048938751220703, "max": 1.425399899482727, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68844.28125, "min": 68301.546875, "max": 79014.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.4991452991453, "min": 76.93613707165109, "max": 419.56302521008405, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49432.0, "min": 49153.0, "max": 49949.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999896.0, "min": 49437.0, "max": 1999896.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999896.0, "min": 49437.0, "max": 1999896.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.452239513397217, "min": 0.1035681739449501, "max": 2.498924970626831, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1434.56005859375, "min": 12.221044540405273, "max": 1570.056640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8339783722518854, "min": 1.9571836201821344, "max": 3.999433077611463, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2242.877347767353, "min": 230.94766718149185, "max": 2422.8382232785225, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8339783722518854, "min": 1.9571836201821344, "max": 3.999433077611463, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2242.877347767353, "min": 230.94766718149185, "max": 2422.8382232785225, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015049487366630072, "min": 0.012696852259523439, "max": 0.022765276452264515, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045148462099890214, "min": 0.025393704519046878, "max": 0.05793671790161171, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05595386164883773, "min": 0.023629334351668755, "max": 0.06198475590596597, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16786158494651318, "min": 0.04725866870333751, "max": 0.17592455769578616, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.924298691933333e-06, "min": 3.924298691933333e-06, "max": 0.0002953527015491, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.17728960758e-05, "min": 1.17728960758e-05, "max": 0.0008442598685800501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130806666666665, "min": 0.10130806666666665, "max": 0.19845090000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039242, "min": 0.20775015000000008, "max": 0.58141995, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.527252666666668e-05, "min": 7.527252666666668e-05, "max": 0.004922699910000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022581758000000005, "min": 0.00022581758000000005, "max": 0.014072855505, "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": "1713808081", "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 --resume", "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": "1713810677" }, "total": 2596.723108898, "count": 1, "self": 0.4900819469999078, "children": { "run_training.setup": { "total": 0.05419136799991975, "count": 1, "self": 0.05419136799991975 }, "TrainerController.start_learning": { "total": 2596.1788355830004, "count": 1, "self": 4.7649593109345005, "children": { "TrainerController._reset_env": { "total": 2.0020793970001023, "count": 1, "self": 2.0020793970001023 }, "TrainerController.advance": { "total": 2589.2775331560656, "count": 232607, "self": 5.025700766068894, "children": { "env_step": { "total": 2086.9151563619785, "count": 232607, "self": 1727.6028383458492, "children": { "SubprocessEnvManager._take_step": { "total": 356.126738949116, "count": 232607, "self": 18.19796660830002, "children": { "TorchPolicy.evaluate": { "total": 337.92877234081595, "count": 222860, "self": 337.92877234081595 } } }, "workers": { "total": 3.1855790670132365, "count": 232607, "self": 0.0, "children": { "worker_root": { "total": 2588.334759235008, "count": 232607, "is_parallel": true, "self": 1197.8526593600297, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009297469999864916, "count": 1, "is_parallel": true, "self": 0.0002644600000394348, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006652869999470568, "count": 2, "is_parallel": true, "self": 0.0006652869999470568 } } }, "UnityEnvironment.step": { "total": 0.03155669099999159, "count": 1, "is_parallel": true, "self": 0.0004132720000598056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020325000002685556, "count": 1, "is_parallel": true, "self": 0.00020325000002685556 }, "communicator.exchange": { "total": 0.030132437999895956, "count": 1, "is_parallel": true, "self": 0.030132437999895956 }, "steps_from_proto": { "total": 0.000807731000008971, "count": 1, "is_parallel": true, "self": 0.00021660400000200752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005911270000069635, "count": 2, "is_parallel": true, "self": 0.0005911270000069635 } } } } } } }, "UnityEnvironment.step": { "total": 1390.482099874978, "count": 232606, "is_parallel": true, "self": 41.13563788602801, "children": { "UnityEnvironment._generate_step_input": { "total": 92.35768089394901, "count": 232606, "is_parallel": true, "self": 92.35768089394901 }, "communicator.exchange": { "total": 1158.7888250850413, "count": 232606, "is_parallel": true, "self": 1158.7888250850413 }, "steps_from_proto": { "total": 98.19995600995969, "count": 232606, "is_parallel": true, "self": 37.47124757703966, "children": { "_process_rank_one_or_two_observation": { "total": 60.72870843292003, "count": 465212, "is_parallel": true, "self": 60.72870843292003 } } } } } } } } } } }, "trainer_advance": { "total": 497.3366760280185, "count": 232607, "self": 6.906317391115522, "children": { "process_trajectory": { "total": 168.4796030269024, "count": 232607, "self": 167.0472153109024, "children": { "RLTrainer._checkpoint": { "total": 1.4323877159999938, "count": 10, "self": 1.4323877159999938 } } }, "_update_policy": { "total": 321.95075561000056, "count": 97, "self": 258.85976934099585, "children": { "TorchPPOOptimizer.update": { "total": 63.0909862690047, "count": 2910, "self": 63.0909862690047 } } } } } } }, "trainer_threads": { "total": 1.3919998309575021e-06, "count": 1, "self": 1.3919998309575021e-06 }, "TrainerController._save_models": { "total": 0.134262327000215, "count": 1, "self": 0.0035568740004237043, "children": { "RLTrainer._checkpoint": { "total": 0.1307054529997913, "count": 1, "self": 0.1307054529997913 } } } } } } }