{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4061716794967651, "min": 1.4061716794967651, "max": 1.4299778938293457, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68922.1015625, "min": 68378.5703125, "max": 75889.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.53979238754326, "min": 81.1414309484193, "max": 403.83870967741933, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49442.0, "min": 48766.0, "max": 50107.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999939.0, "min": 49450.0, "max": 1999939.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999939.0, "min": 49450.0, "max": 1999939.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4149580001831055, "min": 0.21645209193229675, "max": 2.437232732772827, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1395.845703125, "min": 26.623607635498047, "max": 1451.06298828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8249857689682587, "min": 1.8128466310539866, "max": 3.860150159649227, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2210.8417744636536, "min": 222.98013561964035, "max": 2283.082412838936, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8249857689682587, "min": 1.8128466310539866, "max": 3.860150159649227, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2210.8417744636536, "min": 222.98013561964035, "max": 2283.082412838936, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018348140115388864, "min": 0.013719939023818975, "max": 0.021487154260406288, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05504442034616659, "min": 0.02743987804763795, "max": 0.05932566584815504, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057905305052797, "min": 0.022253347964336475, "max": 0.057905305052797, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.173715915158391, "min": 0.04450669592867295, "max": 0.173715915158391, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.552148815983339e-06, "min": 3.552148815983339e-06, "max": 0.000295366876544375, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0656446447950018e-05, "min": 1.0656446447950018e-05, "max": 0.0008443908185363997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118401666666667, "min": 0.10118401666666667, "max": 0.19845562500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30355205, "min": 0.20750304999999997, "max": 0.5814636000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.90824316666668e-05, "min": 6.90824316666668e-05, "max": 0.004922935687500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020724729500000037, "min": 0.00020724729500000037, "max": 0.014075033640000002, "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": "1724882055", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724884568" }, "total": 2513.678929193, "count": 1, "self": 0.4381075679998503, "children": { "run_training.setup": { "total": 0.053410589000122854, "count": 1, "self": 0.053410589000122854 }, "TrainerController.start_learning": { "total": 2513.187411036, "count": 1, "self": 4.461765165919587, "children": { "TrainerController._reset_env": { "total": 2.0921805630000563, "count": 1, "self": 2.0921805630000563 }, "TrainerController.advance": { "total": 2506.5161933820805, "count": 231945, "self": 4.569098273164855, "children": { "env_step": { "total": 1992.9039504978864, "count": 231945, "self": 1574.7449453869197, "children": { "SubprocessEnvManager._take_step": { "total": 415.3035932619912, "count": 231945, "self": 16.294868968922174, "children": { "TorchPolicy.evaluate": { "total": 399.008724293069, "count": 222834, "self": 399.008724293069 } } }, "workers": { "total": 2.8554118489755638, "count": 231945, "self": 0.0, "children": { "worker_root": { "total": 2505.7873787909557, "count": 231945, "is_parallel": true, "self": 1230.4662750838734, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008871340000951022, "count": 1, "is_parallel": true, "self": 0.00027559200020732533, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006115419998877769, "count": 2, "is_parallel": true, "self": 0.0006115419998877769 } } }, "UnityEnvironment.step": { "total": 0.030700821999971595, "count": 1, "is_parallel": true, "self": 0.00036979500009692856, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018376899993199913, "count": 1, "is_parallel": true, "self": 0.00018376899993199913 }, "communicator.exchange": { "total": 0.02940603000001829, "count": 1, "is_parallel": true, "self": 0.02940603000001829 }, "steps_from_proto": { "total": 0.0007412279999243765, "count": 1, "is_parallel": true, "self": 0.0002199719999680383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005212559999563382, "count": 2, "is_parallel": true, "self": 0.0005212559999563382 } } } } } } }, "UnityEnvironment.step": { "total": 1275.3211037070823, "count": 231944, "is_parallel": true, "self": 38.03338547106273, "children": { "UnityEnvironment._generate_step_input": { "total": 85.05358773502576, "count": 231944, "is_parallel": true, "self": 85.05358773502576 }, "communicator.exchange": { "total": 1060.681289623966, "count": 231944, "is_parallel": true, "self": 1060.681289623966 }, "steps_from_proto": { "total": 91.55284087702785, "count": 231944, "is_parallel": true, "self": 34.58974340717964, "children": { "_process_rank_one_or_two_observation": { "total": 56.96309746984821, "count": 463888, "is_parallel": true, "self": 56.96309746984821 } } } } } } } } } } }, "trainer_advance": { "total": 509.0431446110292, "count": 231945, "self": 6.482760445020176, "children": { "process_trajectory": { "total": 162.3007387210091, "count": 231945, "self": 160.8714565280086, "children": { "RLTrainer._checkpoint": { "total": 1.4292821930005175, "count": 10, "self": 1.4292821930005175 } } }, "_update_policy": { "total": 340.25964544499993, "count": 97, "self": 273.509339460996, "children": { "TorchPPOOptimizer.update": { "total": 66.75030598400394, "count": 2910, "self": 66.75030598400394 } } } } } } }, "trainer_threads": { "total": 9.259997568733525e-07, "count": 1, "self": 9.259997568733525e-07 }, "TrainerController._save_models": { "total": 0.11727099900008398, "count": 1, "self": 0.001877109000361088, "children": { "RLTrainer._checkpoint": { "total": 0.11539388999972289, "count": 1, "self": 0.11539388999972289 } } } } } } }