{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4032610654830933, "min": 1.4032610654830933, "max": 1.4290275573730469, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70198.1328125, "min": 69267.265625, "max": 77004.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.79005524861878, "min": 80.2390243902439, "max": 402.85483870967744, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49842.0, "min": 48710.0, "max": 50082.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999857.0, "min": 49941.0, "max": 1999857.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999857.0, "min": 49941.0, "max": 1999857.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.441159248352051, "min": 0.0977514311671257, "max": 2.485295295715332, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1325.5494384765625, "min": 12.023426055908203, "max": 1506.4666748046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.763718887038433, "min": 1.8917136434617081, "max": 4.033910231989694, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2043.699355661869, "min": 232.6807781457901, "max": 2383.1694727540016, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.763718887038433, "min": 1.8917136434617081, "max": 4.033910231989694, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2043.699355661869, "min": 232.6807781457901, "max": 2383.1694727540016, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0186678880769048, "min": 0.013339127875709286, "max": 0.020879148038996695, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.056003664230714394, "min": 0.02667825575141857, "max": 0.06109786165834521, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05414946348302894, "min": 0.02077243089055022, "max": 0.06433689755698045, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16244839044908682, "min": 0.04154486178110044, "max": 0.1846834037452936, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.548248817283328e-06, "min": 3.548248817283328e-06, "max": 0.000295285426571525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0644746451849984e-05, "min": 1.0644746451849984e-05, "max": 0.0008437501687499499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118271666666667, "min": 0.10118271666666667, "max": 0.19842847500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30354815, "min": 0.20751894999999998, "max": 0.58125005, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.901756166666658e-05, "min": 6.901756166666658e-05, "max": 0.0049215809025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020705268499999975, "min": 0.00020705268499999975, "max": 0.014064377494999999, "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": "1686659753", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686662066" }, "total": 2313.373164092, "count": 1, "self": 0.438033945999905, "children": { "run_training.setup": { "total": 0.03903810299993893, "count": 1, "self": 0.03903810299993893 }, "TrainerController.start_learning": { "total": 2312.896092043, "count": 1, "self": 4.211699368994687, "children": { "TrainerController._reset_env": { "total": 4.606654269999922, "count": 1, "self": 4.606654269999922 }, "TrainerController.advance": { "total": 2303.9636914770053, "count": 232920, "self": 4.266338775003078, "children": { "env_step": { "total": 1795.3808481560159, "count": 232920, "self": 1514.618867446131, "children": { "SubprocessEnvManager._take_step": { "total": 278.139903951969, "count": 232920, "self": 15.722329074876711, "children": { "TorchPolicy.evaluate": { "total": 262.4175748770923, "count": 223015, "self": 262.4175748770923 } } }, "workers": { "total": 2.6220767579158064, "count": 232920, "self": 0.0, "children": { "worker_root": { "total": 2305.6234232060337, "count": 232920, "is_parallel": true, "self": 1065.5834090800558, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010883649999868794, "count": 1, "is_parallel": true, "self": 0.00031280499990771204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007755600000791674, "count": 2, "is_parallel": true, "self": 0.0007755600000791674 } } }, "UnityEnvironment.step": { "total": 0.06474586000001636, "count": 1, "is_parallel": true, "self": 0.0005197810000936443, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002116340000384298, "count": 1, "is_parallel": true, "self": 0.0002116340000384298 }, "communicator.exchange": { "total": 0.06324305399994046, "count": 1, "is_parallel": true, "self": 0.06324305399994046 }, "steps_from_proto": { "total": 0.0007713909999438329, "count": 1, "is_parallel": true, "self": 0.0002481069999475949, "children": { "_process_rank_one_or_two_observation": { "total": 0.000523283999996238, "count": 2, "is_parallel": true, "self": 0.000523283999996238 } } } } } } }, "UnityEnvironment.step": { "total": 1240.040014125978, "count": 232919, "is_parallel": true, "self": 37.64385302117353, "children": { "UnityEnvironment._generate_step_input": { "total": 75.39359862591584, "count": 232919, "is_parallel": true, "self": 75.39359862591584 }, "communicator.exchange": { "total": 1036.232974019892, "count": 232919, "is_parallel": true, "self": 1036.232974019892 }, "steps_from_proto": { "total": 90.76958845899662, "count": 232919, "is_parallel": true, "self": 32.92648769203083, "children": { "_process_rank_one_or_two_observation": { "total": 57.84310076696579, "count": 465838, "is_parallel": true, "self": 57.84310076696579 } } } } } } } } } } }, "trainer_advance": { "total": 504.3165045459864, "count": 232920, "self": 6.398308378989668, "children": { "process_trajectory": { "total": 131.8979222649981, "count": 232920, "self": 130.67406687199832, "children": { "RLTrainer._checkpoint": { "total": 1.2238553929997806, "count": 10, "self": 1.2238553929997806 } } }, "_update_policy": { "total": 366.0202739019986, "count": 97, "self": 308.72440478299427, "children": { "TorchPPOOptimizer.update": { "total": 57.29586911900435, "count": 2910, "self": 57.29586911900435 } } } } } } }, "trainer_threads": { "total": 9.479999789618887e-07, "count": 1, "self": 9.479999789618887e-07 }, "TrainerController._save_models": { "total": 0.11404597899991131, "count": 1, "self": 0.0022234540001591085, "children": { "RLTrainer._checkpoint": { "total": 0.1118225249997522, "count": 1, "self": 0.1118225249997522 } } } } } } }