{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4078370332717896, "min": 1.4078370332717896, "max": 1.4335445165634155, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70572.0546875, "min": 69242.125, "max": 76806.3671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.59380097879283, "min": 80.59380097879283, "max": 385.2923076923077, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49404.0, "min": 48903.0, "max": 50088.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999955.0, "min": 49774.0, "max": 1999955.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999955.0, "min": 49774.0, "max": 1999955.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4349005222320557, "min": 0.0986761674284935, "max": 2.4663069248199463, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1492.593994140625, "min": 12.729225158691406, "max": 1501.98095703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.805985028066993, "min": 1.796454133335934, "max": 3.9763108212536156, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2333.0688222050667, "min": 231.7425832003355, "max": 2373.570513367653, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.805985028066993, "min": 1.796454133335934, "max": 3.9763108212536156, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2333.0688222050667, "min": 231.7425832003355, "max": 2373.570513367653, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014603435159854903, "min": 0.013774176820273473, "max": 0.02125818882001719, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04381030547956471, "min": 0.027548353640546946, "max": 0.05556174880475737, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0619048837158415, "min": 0.020875933735320963, "max": 0.0619048837158415, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1857146511475245, "min": 0.041751867470641926, "max": 0.1857146511475245, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6666987777999977e-06, "min": 3.6666987777999977e-06, "max": 0.00029536845154384995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1000096333399994e-05, "min": 1.1000096333399994e-05, "max": 0.0008442174185941997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122220000000003, "min": 0.10122220000000003, "max": 0.19845615000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366660000000006, "min": 0.20757029999999999, "max": 0.5814058, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.098777999999996e-05, "min": 7.098777999999996e-05, "max": 0.004922961885000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002129633399999999, "min": 0.0002129633399999999, "max": 0.014072149419999996, "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": "1779703782", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy_UNITY_IS_BULLSHIT --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1779706487" }, "total": 2705.233342678, "count": 1, "self": 0.8423076349999974, "children": { "run_training.setup": { "total": 0.06448772900000677, "count": 1, "self": 0.06448772900000677 }, "TrainerController.start_learning": { "total": 2704.326547314, "count": 1, "self": 4.497036156965805, "children": { "TrainerController._reset_env": { "total": 2.3305638360000103, "count": 1, "self": 2.3305638360000103 }, "TrainerController.advance": { "total": 2697.3106124000337, "count": 232345, "self": 5.0429575070356805, "children": { "env_step": { "total": 2190.4147461340362, "count": 232345, "self": 1751.359137565119, "children": { "SubprocessEnvManager._take_step": { "total": 436.0833112619742, "count": 232345, "self": 16.419455230952394, "children": { "TorchPolicy.evaluate": { "total": 419.6638560310218, "count": 222918, "self": 419.6638560310218 } } }, "workers": { "total": 2.9722973069430623, "count": 232345, "self": 0.0, "children": { "worker_root": { "total": 2692.5124757950716, "count": 232345, "is_parallel": true, "self": 1278.18900225608, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008643789999496221, "count": 1, "is_parallel": true, "self": 0.0002497269999821583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006146519999674638, "count": 2, "is_parallel": true, "self": 0.0006146519999674638 } } }, "UnityEnvironment.step": { "total": 0.03217265799997904, "count": 1, "is_parallel": true, "self": 0.0004335049999895091, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000210305999985394, "count": 1, "is_parallel": true, "self": 0.000210305999985394 }, "communicator.exchange": { "total": 0.03082755799999859, "count": 1, "is_parallel": true, "self": 0.03082755799999859 }, "steps_from_proto": { "total": 0.000701289000005545, "count": 1, "is_parallel": true, "self": 0.00023321100007933637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004680779999262086, "count": 2, "is_parallel": true, "self": 0.0004680779999262086 } } } } } } }, "UnityEnvironment.step": { "total": 1414.3234735389917, "count": 232344, "is_parallel": true, "self": 39.552280100200505, "children": { "UnityEnvironment._generate_step_input": { "total": 90.22782661986571, "count": 232344, "is_parallel": true, "self": 90.22782661986571 }, "communicator.exchange": { "total": 1190.9352630069914, "count": 232344, "is_parallel": true, "self": 1190.9352630069914 }, "steps_from_proto": { "total": 93.60810381193403, "count": 232344, "is_parallel": true, "self": 34.640604037993455, "children": { "_process_rank_one_or_two_observation": { "total": 58.967499773940574, "count": 464688, "is_parallel": true, "self": 58.967499773940574 } } } } } } } } } } }, "trainer_advance": { "total": 501.8529087589618, "count": 232345, "self": 6.9426229670636985, "children": { "process_trajectory": { "total": 165.34572597290133, "count": 232345, "self": 164.0169840529009, "children": { "RLTrainer._checkpoint": { "total": 1.3287419200004251, "count": 10, "self": 1.3287419200004251 } } }, "_update_policy": { "total": 329.56455981899677, "count": 97, "self": 263.1124679160008, "children": { "TorchPPOOptimizer.update": { "total": 66.45209190299596, "count": 2910, "self": 66.45209190299596 } } } } } } }, "trainer_threads": { "total": 1.9019998944713734e-06, "count": 1, "self": 1.9019998944713734e-06 }, "TrainerController._save_models": { "total": 0.18833301900031074, "count": 1, "self": 0.002349064000100043, "children": { "RLTrainer._checkpoint": { "total": 0.1859839550002107, "count": 1, "self": 0.1859839550002107 } } } } } } }