{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4051218032836914, "min": 1.4051218032836914, "max": 1.4289029836654663, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68603.6640625, "min": 68257.84375, "max": 76243.90625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 108.87692307692308, "min": 92.78048780487805, "max": 414.11570247933884, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49539.0, "min": 48792.0, "max": 50173.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49809.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49809.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.312967538833618, "min": 0.04131506383419037, "max": 2.385871410369873, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1052.4002685546875, "min": 4.957807540893555, "max": 1258.5595703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.593555980986291, "min": 1.890068710098664, "max": 3.884828919611479, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1635.0679713487625, "min": 226.80824521183968, "max": 2015.9850631952286, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.593555980986291, "min": 1.890068710098664, "max": 3.884828919611479, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1635.0679713487625, "min": 226.80824521183968, "max": 2015.9850631952286, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01575221528845658, "min": 0.01340871254603068, "max": 0.0222302296004879, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04725664586536974, "min": 0.02681742509206136, "max": 0.06133199017785955, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.047253799479868665, "min": 0.023272700452556215, "max": 0.05512282457202673, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.141761398439606, "min": 0.04654540090511243, "max": 0.16052199974656106, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.328948890383339e-06, "min": 3.328948890383339e-06, "max": 0.00029536620154459994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.986846671150017e-06, "min": 9.986846671150017e-06, "max": 0.0008441487186170999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011096166666667, "min": 0.1011096166666667, "max": 0.19845539999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033288500000001, "min": 0.20740139999999996, "max": 0.5813828999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.536987166666676e-05, "min": 6.536987166666676e-05, "max": 0.004922924460000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019610961500000028, "min": 0.00019610961500000028, "max": 0.01407100671, "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": "1710909472", "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", "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": "1710912082" }, "total": 2609.875911826, "count": 1, "self": 0.44254949700007273, "children": { "run_training.setup": { "total": 0.06260084000007282, "count": 1, "self": 0.06260084000007282 }, "TrainerController.start_learning": { "total": 2609.370761489, "count": 1, "self": 4.759377438905631, "children": { "TrainerController._reset_env": { "total": 3.5677072510000016, "count": 1, "self": 3.5677072510000016 }, "TrainerController.advance": { "total": 2600.931659780094, "count": 231604, "self": 5.085917329054155, "children": { "env_step": { "total": 2090.0850567261073, "count": 231604, "self": 1729.0228890111853, "children": { "SubprocessEnvManager._take_step": { "total": 357.93728318891783, "count": 231604, "self": 19.202981585815564, "children": { "TorchPolicy.evaluate": { "total": 338.73430160310227, "count": 222956, "self": 338.73430160310227 } } }, "workers": { "total": 3.12488452600428, "count": 231604, "self": 0.0, "children": { "worker_root": { "total": 2601.576467111984, "count": 231604, "is_parallel": true, "self": 1204.0516773350832, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010024819999898682, "count": 1, "is_parallel": true, "self": 0.00025677899998299836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007457030000068698, "count": 2, "is_parallel": true, "self": 0.0007457030000068698 } } }, "UnityEnvironment.step": { "total": 0.03472541000007823, "count": 1, "is_parallel": true, "self": 0.0005348350001668223, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002635800000234667, "count": 1, "is_parallel": true, "self": 0.0002635800000234667 }, "communicator.exchange": { "total": 0.032926699999961784, "count": 1, "is_parallel": true, "self": 0.032926699999961784 }, "steps_from_proto": { "total": 0.0010002949999261546, "count": 1, "is_parallel": true, "self": 0.00025193399994805077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007483609999781038, "count": 2, "is_parallel": true, "self": 0.0007483609999781038 } } } } } } }, "UnityEnvironment.step": { "total": 1397.524789776901, "count": 231603, "is_parallel": true, "self": 43.05870271888307, "children": { "UnityEnvironment._generate_step_input": { "total": 87.73055494200037, "count": 231603, "is_parallel": true, "self": 87.73055494200037 }, "communicator.exchange": { "total": 1167.0059066601073, "count": 231603, "is_parallel": true, "self": 1167.0059066601073 }, "steps_from_proto": { "total": 99.7296254559102, "count": 231603, "is_parallel": true, "self": 34.794063182793934, "children": { "_process_rank_one_or_two_observation": { "total": 64.93556227311626, "count": 463206, "is_parallel": true, "self": 64.93556227311626 } } } } } } } } } } }, "trainer_advance": { "total": 505.7606857249324, "count": 231604, "self": 7.796658073893468, "children": { "process_trajectory": { "total": 150.7162383010383, "count": 231604, "self": 149.40606112403827, "children": { "RLTrainer._checkpoint": { "total": 1.3101771770000141, "count": 10, "self": 1.3101771770000141 } } }, "_update_policy": { "total": 347.24778935000063, "count": 97, "self": 281.4580570999997, "children": { "TorchPPOOptimizer.update": { "total": 65.78973225000095, "count": 2910, "self": 65.78973225000095 } } } } } } }, "trainer_threads": { "total": 9.350001164420974e-07, "count": 1, "self": 9.350001164420974e-07 }, "TrainerController._save_models": { "total": 0.1120160840000608, "count": 1, "self": 0.0020264530003260006, "children": { "RLTrainer._checkpoint": { "total": 0.1099896309997348, "count": 1, "self": 0.1099896309997348 } } } } } } }