{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 0.44570162892341614, "min": 0.4457007050514221, "max": 0.4476816654205322, "count": 41 }, "Huggy.Policy.Entropy.sum": { "value": 24067.888671875, "min": 18050.89453125, "max": 24174.62890625, "count": 41 }, "Huggy.Environment.EpisodeLength.mean": { "value": 749.0, "min": 738.6805555555555, "max": 749.0, "count": 41 }, "Huggy.Environment.EpisodeLength.sum": { "value": 53928.0, "min": 40446.0, "max": 53928.0, "count": 41 }, "Huggy.Step.mean": { "value": 49999543.0, "min": 47999293.0, "max": 49999543.0, "count": 41 }, "Huggy.Step.sum": { "value": 49999543.0, "min": 47999293.0, "max": 49999543.0, "count": 41 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00971367210149765, "min": 0.009701162576675415, "max": 0.35220038890838623, "count": 41 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 0.650816023349762, "min": 0.6499779224395752, "max": 20.779823303222656, "count": 41 }, "Huggy.Environment.CumulativeReward.mean": { "value": 0.023240400992556295, "min": 0.018423801948274695, "max": 0.039091974275849636, "count": 41 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1.5571068665012717, "min": 1.2343947305344045, "max": 2.3064264822751284, "count": 41 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 0.023240400992556295, "min": 0.018423801948274695, "max": 0.039091974275849636, "count": 41 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1.5571068665012717, "min": 1.2343947305344045, "max": 2.3064264822751284, "count": 41 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017997478525219962, "min": 0.012774279367220469, "max": 0.02040528528437463, "count": 41 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.035994957050439924, "min": 0.015146567626521947, "max": 0.04081057056874926, "count": 41 }, "Huggy.Losses.ValueLoss.mean": { "value": 3.148630357594439e-05, "min": 2.675114643725698e-05, "max": 0.005304624336228396, "count": 41 }, "Huggy.Losses.ValueLoss.sum": { "value": 6.297260715188878e-05, "min": 2.675114643725698e-05, "max": 0.005304624336228396, "count": 41 }, "Huggy.Policy.LearningRate.mean": { "value": 2.008419330859872e-07, "min": 2.008419330859872e-07, "max": 1.210783796408599e-05, "count": 41 }, "Huggy.Policy.LearningRate.sum": { "value": 4.016838661719744e-07, "min": 4.016838661719744e-07, "max": 2.3729676090171985e-05, "count": 41 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10006691399999999, "min": 0.10006691399999999, "max": 0.10403591399999998, "count": 41 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20013382799999999, "min": 0.10014791399999999, "max": 0.20790982800000002, "count": 41 }, "Huggy.Policy.Beta.mean": { "value": 1.333900859999979e-05, "min": 1.333900859999979e-05, "max": 0.00021139210859999984, "count": 41 }, "Huggy.Policy.Beta.sum": { "value": 2.667801719999958e-05, "min": 1.7380908600000234e-05, "max": 0.00041470041719999986, "count": 41 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 41 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 41 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1749597981", "python_version": "3.10.12 (main, Jun 9 2025, 22:13:44) [GCC 13.3.0]", "command_line_arguments": "/home/robert/.pyenv/versions/.venv10/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749600907" }, "total": 2926.3618206200044, "count": 1, "self": 0.7106918019999284, "children": { "run_training.setup": { "total": 0.0954735260020243, "count": 1, "self": 0.0954735260020243 }, "TrainerController.start_learning": { "total": 2925.5556552920025, "count": 1, "self": 5.602474036277272, "children": { "TrainerController._reset_env": { "total": 31.417660179009545, "count": 1, "self": 31.417660179009545 }, "TrainerController.advance": { "total": 2888.132637700721, "count": 228152, "self": 5.762832497042837, "children": { "env_step": { "total": 2413.2486994336796, "count": 228152, "self": 1715.891698917796, "children": { "SubprocessEnvManager._take_step": { "total": 693.60937842571, "count": 228152, "self": 22.312184159309254, "children": { "TorchPolicy.evaluate": { "total": 671.2971942664008, "count": 228000, "self": 671.2971942664008 } } }, "workers": { "total": 3.747622090173536, "count": 228152, "self": 0.0, "children": { "worker_root": { "total": 2913.173422230946, "count": 228152, "is_parallel": true, "self": 1519.0779936310719, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008895350038073957, "count": 1, "is_parallel": true, "self": 0.0002130550128640607, "children": { "_process_rank_one_or_two_observation": { "total": 0.000676479990943335, "count": 2, "is_parallel": true, "self": 0.000676479990943335 } } }, "UnityEnvironment.step": { "total": 0.020831902002100833, "count": 1, "is_parallel": true, "self": 0.0001848150131991133, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00011206699127797037, "count": 1, "is_parallel": true, "self": 0.00011206699127797037 }, "communicator.exchange": { "total": 0.020128763993852772, "count": 1, "is_parallel": true, "self": 0.020128763993852772 }, "steps_from_proto": { "total": 0.00040625600377097726, "count": 1, "is_parallel": true, "self": 9.690001024864614e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003093559935223311, "count": 2, "is_parallel": true, "self": 0.0003093559935223311 } } } } } } }, "UnityEnvironment.step": { "total": 1394.0954285998741, "count": 228151, "is_parallel": true, "self": 29.297776297826204, "children": { "UnityEnvironment._generate_step_input": { "total": 51.404873475417844, "count": 228151, "is_parallel": true, "self": 51.404873475417844 }, "communicator.exchange": { "total": 1248.190876835084, "count": 228151, "is_parallel": true, "self": 1248.190876835084 }, "steps_from_proto": { "total": 65.20190199154604, "count": 228151, "is_parallel": true, "self": 22.15502689029381, "children": { "_process_rank_one_or_two_observation": { "total": 43.046875101252226, "count": 456302, "is_parallel": true, "self": 43.046875101252226 } } } } } } } } } } }, "trainer_advance": { "total": 469.1211057699984, "count": 228152, "self": 6.222112682109582, "children": { "process_trajectory": { "total": 117.81837346493558, "count": 228152, "self": 114.65308970793558, "children": { "RLTrainer._checkpoint": { "total": 3.1652837569999974, "count": 11, "self": 3.1652837569999974 } } }, "_update_policy": { "total": 345.08061962295324, "count": 75, "self": 266.1874715768063, "children": { "TorchPPOOptimizer.update": { "total": 78.89314804614696, "count": 2922, "self": 78.89314804614696 } } } } } } }, "trainer_threads": { "total": 8.729984983801842e-07, "count": 1, "self": 8.729984983801842e-07 }, "TrainerController._save_models": { "total": 0.40288250299636275, "count": 1, "self": 0.07676358298340347, "children": { "RLTrainer._checkpoint": { "total": 0.3261189200129593, "count": 1, "self": 0.3261189200129593 } } } } } } }