{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3990575075149536, "min": 1.3990451097488403, "max": 1.42495858669281, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68134.1015625, "min": 67941.125, "max": 77000.1953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.48703703703704, "min": 84.28373702422145, "max": 433.62931034482756, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49403.0, "min": 48716.0, "max": 50301.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999986.0, "min": 49887.0, "max": 1999986.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999986.0, "min": 49887.0, "max": 1999986.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4351885318756104, "min": 0.06366197764873505, "max": 2.4589452743530273, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1315.0018310546875, "min": 7.321127414703369, "max": 1393.6141357421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.804830888686357, "min": 2.015466143255648, "max": 3.8532676530517707, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2054.6086798906326, "min": 231.77860647439957, "max": 2183.5536318421364, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.804830888686357, "min": 2.015466143255648, "max": 3.8532676530517707, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2054.6086798906326, "min": 231.77860647439957, "max": 2183.5536318421364, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01705423949978366, "min": 0.01270237111239112, "max": 0.019561243987118362, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05116271849935098, "min": 0.02540474222478224, "max": 0.05868373196135508, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05901901423931122, "min": 0.022768922957281272, "max": 0.060202356634868524, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17705704271793365, "min": 0.045537845914562544, "max": 0.18060706990460557, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2557989147666723e-06, "min": 3.2557989147666723e-06, "max": 0.000295357576547475, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.767396744300017e-06, "min": 9.767396744300017e-06, "max": 0.0008440216686594499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108523333333332, "min": 0.10108523333333332, "max": 0.198452525, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30325569999999996, "min": 0.20731360000000001, "max": 0.5813405500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.415314333333344e-05, "min": 6.415314333333344e-05, "max": 0.0049227809975, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001924594300000003, "min": 0.0001924594300000003, "max": 0.014068893445, "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": "1703155674", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703158274" }, "total": 2600.3058780470005, "count": 1, "self": 0.44917322800074544, "children": { "run_training.setup": { "total": 0.054094410999823594, "count": 1, "self": 0.054094410999823594 }, "TrainerController.start_learning": { "total": 2599.802610408, "count": 1, "self": 5.100252200830255, "children": { "TrainerController._reset_env": { "total": 3.4383787790002316, "count": 1, "self": 3.4383787790002316 }, "TrainerController.advance": { "total": 2591.156159822169, "count": 232032, "self": 5.304649436948694, "children": { "env_step": { "total": 2084.854386486107, "count": 232032, "self": 1733.087677338026, "children": { "SubprocessEnvManager._take_step": { "total": 348.37094684604926, "count": 232032, "self": 18.2329912193145, "children": { "TorchPolicy.evaluate": { "total": 330.13795562673477, "count": 222848, "self": 330.13795562673477 } } }, "workers": { "total": 3.395762302031926, "count": 232032, "self": 0.0, "children": { "worker_root": { "total": 2591.836581766329, "count": 232032, "is_parallel": true, "self": 1188.8677729714777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000726966000001994, "count": 1, "is_parallel": true, "self": 0.00019144299994877656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005355230000532174, "count": 2, "is_parallel": true, "self": 0.0005355230000532174 } } }, "UnityEnvironment.step": { "total": 0.04517192999992403, "count": 1, "is_parallel": true, "self": 0.00032058299984782934, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018734900004346855, "count": 1, "is_parallel": true, "self": 0.00018734900004346855 }, "communicator.exchange": { "total": 0.04397521700002471, "count": 1, "is_parallel": true, "self": 0.04397521700002471 }, "steps_from_proto": { "total": 0.0006887810000080208, "count": 1, "is_parallel": true, "self": 0.00017080199995689327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005179790000511275, "count": 2, "is_parallel": true, "self": 0.0005179790000511275 } } } } } } }, "UnityEnvironment.step": { "total": 1402.9688087948512, "count": 232031, "is_parallel": true, "self": 43.31237682226356, "children": { "UnityEnvironment._generate_step_input": { "total": 84.53699341627089, "count": 232031, "is_parallel": true, "self": 84.53699341627089 }, "communicator.exchange": { "total": 1177.3668419091864, "count": 232031, "is_parallel": true, "self": 1177.3668419091864 }, "steps_from_proto": { "total": 97.7525966471303, "count": 232031, "is_parallel": true, "self": 33.36564340168525, "children": { "_process_rank_one_or_two_observation": { "total": 64.38695324544506, "count": 464062, "is_parallel": true, "self": 64.38695324544506 } } } } } } } } } } }, "trainer_advance": { "total": 500.9971238991129, "count": 232032, "self": 8.02776983105423, "children": { "process_trajectory": { "total": 164.13952001705547, "count": 232032, "self": 162.92625349905393, "children": { "RLTrainer._checkpoint": { "total": 1.2132665180015465, "count": 10, "self": 1.2132665180015465 } } }, "_update_policy": { "total": 328.8298340510032, "count": 97, "self": 263.0901601230057, "children": { "TorchPPOOptimizer.update": { "total": 65.7396739279975, "count": 2910, "self": 65.7396739279975 } } } } } } }, "trainer_threads": { "total": 8.690003596711904e-07, "count": 1, "self": 8.690003596711904e-07 }, "TrainerController._save_models": { "total": 0.10781873700034339, "count": 1, "self": 0.0019696640001711785, "children": { "RLTrainer._checkpoint": { "total": 0.10584907300017221, "count": 1, "self": 0.10584907300017221 } } } } } } }