{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4061150550842285, "min": 1.4061049222946167, "max": 1.4303351640701294, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69220.234375, "min": 67911.328125, "max": 80360.265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 117.23349056603773, "min": 99.44689378757515, "max": 399.536, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49707.0, "min": 48862.0, "max": 50260.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999475.0, "min": 49317.0, "max": 1999475.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999475.0, "min": 49317.0, "max": 1999475.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.358470916748047, "min": 0.12814180552959442, "max": 2.4001271724700928, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 999.99169921875, "min": 15.8895845413208, "max": 1175.589599609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.627215542742666, "min": 1.7787129042610046, "max": 3.815696732723417, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1537.9393901228905, "min": 220.56040012836456, "max": 1843.3769235610962, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.627215542742666, "min": 1.7787129042610046, "max": 3.815696732723417, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1537.9393901228905, "min": 220.56040012836456, "max": 1843.3769235610962, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015945184543740727, "min": 0.013591300808669379, "max": 0.018957894842120973, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.031890369087481454, "min": 0.027182601617338757, "max": 0.05682293532202796, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04388154180099567, "min": 0.021042022109031677, "max": 0.06010824323942264, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08776308360199134, "min": 0.04208404421806335, "max": 0.1706496521830559, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.583048472349992e-06, "min": 4.583048472349992e-06, "max": 0.00029536162654612505, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.166096944699984e-06, "min": 9.166096944699984e-06, "max": 0.00084393496868835, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10152765000000004, "min": 0.10152765000000004, "max": 0.19845387499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20305530000000008, "min": 0.20305530000000008, "max": 0.5813116500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.622973499999987e-05, "min": 8.622973499999987e-05, "max": 0.004922848362500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017245946999999974, "min": 0.00017245946999999974, "max": 0.014067451335000002, "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": "1695547388", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --force --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": "1695550025" }, "total": 2637.0359531560002, "count": 1, "self": 0.42359783800020523, "children": { "run_training.setup": { "total": 0.038153340999997454, "count": 1, "self": 0.038153340999997454 }, "TrainerController.start_learning": { "total": 2636.574201977, "count": 1, "self": 4.930104003775796, "children": { "TrainerController._reset_env": { "total": 4.094431692999933, "count": 1, "self": 4.094431692999933 }, "TrainerController.advance": { "total": 2627.432215585225, "count": 231004, "self": 5.042437372369477, "children": { "env_step": { "total": 2053.2290409588495, "count": 231004, "self": 1730.9712279866835, "children": { "SubprocessEnvManager._take_step": { "total": 319.08343144711307, "count": 231004, "self": 18.016390227887314, "children": { "TorchPolicy.evaluate": { "total": 301.06704121922576, "count": 222954, "self": 301.06704121922576 } } }, "workers": { "total": 3.1743815250529224, "count": 231004, "self": 0.0, "children": { "worker_root": { "total": 2628.291341704116, "count": 231004, "is_parallel": true, "self": 1217.92249125116, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000951748000261432, "count": 1, "is_parallel": true, "self": 0.00027472300052977516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006770249997316569, "count": 2, "is_parallel": true, "self": 0.0006770249997316569 } } }, "UnityEnvironment.step": { "total": 0.03358279899975969, "count": 1, "is_parallel": true, "self": 0.0002915099998972437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000216420000015205, "count": 1, "is_parallel": true, "self": 0.000216420000015205 }, "communicator.exchange": { "total": 0.032304596999892965, "count": 1, "is_parallel": true, "self": 0.032304596999892965 }, "steps_from_proto": { "total": 0.0007702719999542751, "count": 1, "is_parallel": true, "self": 0.0002439359996060375, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005263360003482376, "count": 2, "is_parallel": true, "self": 0.0005263360003482376 } } } } } } }, "UnityEnvironment.step": { "total": 1410.368850452956, "count": 231003, "is_parallel": true, "self": 41.62032834716729, "children": { "UnityEnvironment._generate_step_input": { "total": 90.62430422289572, "count": 231003, "is_parallel": true, "self": 90.62430422289572 }, "communicator.exchange": { "total": 1172.6712228459783, "count": 231003, "is_parallel": true, "self": 1172.6712228459783 }, "steps_from_proto": { "total": 105.45299503691467, "count": 231003, "is_parallel": true, "self": 39.36905014185595, "children": { "_process_rank_one_or_two_observation": { "total": 66.08394489505872, "count": 462006, "is_parallel": true, "self": 66.08394489505872 } } } } } } } } } } }, "trainer_advance": { "total": 569.1607372540061, "count": 231004, "self": 7.135515914989355, "children": { "process_trajectory": { "total": 144.77805949101685, "count": 231004, "self": 143.33278930501865, "children": { "RLTrainer._checkpoint": { "total": 1.4452701859981971, "count": 10, "self": 1.4452701859981971 } } }, "_update_policy": { "total": 417.2471618479999, "count": 96, "self": 355.9703409330068, "children": { "TorchPPOOptimizer.update": { "total": 61.276820914993095, "count": 2880, "self": 61.276820914993095 } } } } } } }, "trainer_threads": { "total": 8.549995982320979e-07, "count": 1, "self": 8.549995982320979e-07 }, "TrainerController._save_models": { "total": 0.11744983999960823, "count": 1, "self": 0.0021149049998712144, "children": { "RLTrainer._checkpoint": { "total": 0.11533493499973702, "count": 1, "self": 0.11533493499973702 } } } } } } }