{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4011577367782593, "min": 1.4011577367782593, "max": 1.429830551147461, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68667.9375, "min": 67766.921875, "max": 76576.875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.98360655737704, "min": 78.60932475884245, "max": 433.17241379310343, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49400.0, "min": 48895.0, "max": 50311.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999981.0, "min": 49618.0, "max": 1999981.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999981.0, "min": 49618.0, "max": 1999981.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.425565481185913, "min": 0.026429228484630585, "max": 2.46152400970459, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1479.594970703125, "min": 3.0393612384796143, "max": 1479.594970703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7444462868033863, "min": 1.7746146082878114, "max": 3.903396407220316, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2284.1122349500656, "min": 204.0806799530983, "max": 2305.8147135972977, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7444462868033863, "min": 1.7746146082878114, "max": 3.903396407220316, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2284.1122349500656, "min": 204.0806799530983, "max": 2305.8147135972977, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01662926022391831, "min": 0.013073581452772487, "max": 0.02160666468747271, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04988778067175493, "min": 0.026147162905544974, "max": 0.05521746926242485, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06002624606092771, "min": 0.022363611683249473, "max": 0.06502212348083655, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18007873818278314, "min": 0.044727223366498946, "max": 0.18213059355815253, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.216548927850003e-06, "min": 3.216548927850003e-06, "max": 0.0002953654515448499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.649646783550009e-06, "min": 9.649646783550009e-06, "max": 0.0008440035186654999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107214999999996, "min": 0.10107214999999996, "max": 0.19845515000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30321644999999986, "min": 0.20734309999999995, "max": 0.5813345000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.350028500000007e-05, "min": 6.350028500000007e-05, "max": 0.004922911985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001905008550000002, "min": 0.0001905008550000002, "max": 0.014068591549999999, "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": "1670953807", "python_version": "3.9.16 (main, Dec 13 2022, 18:20:33) \n[GCC 11.3.0]", "command_line_arguments": "/home/markus/src/ai/ml-agents/.venv/bin/mlagents-learn ./config/ppo/Huggy.yaml --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": "1670958557" }, "total": 4749.398941110001, "count": 1, "self": 0.4888778460008325, "children": { "run_training.setup": { "total": 0.04401721000249381, "count": 1, "self": 0.04401721000249381 }, "TrainerController.start_learning": { "total": 4748.866046053998, "count": 1, "self": 10.545487796804082, "children": { "TrainerController._reset_env": { "total": 2.083841329000279, "count": 1, "self": 2.083841329000279 }, "TrainerController.advance": { "total": 4736.0040272541955, "count": 231969, "self": 11.391401876724558, "children": { "env_step": { "total": 2985.543389261493, "count": 231969, "self": 2480.7295454924424, "children": { "SubprocessEnvManager._take_step": { "total": 498.3651150776641, "count": 231969, "self": 37.489012846872356, "children": { "TorchPolicy.evaluate": { "total": 460.87610223079173, "count": 222863, "self": 460.87610223079173 } } }, "workers": { "total": 6.44872869138635, "count": 231969, "self": 0.0, "children": { "worker_root": { "total": 4729.611465101341, "count": 231969, "is_parallel": true, "self": 2876.212790744845, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001524350002000574, "count": 1, "is_parallel": true, "self": 0.0005632829997921363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009610670022084378, "count": 2, "is_parallel": true, "self": 0.0009610670022084378 } } }, "UnityEnvironment.step": { "total": 0.032548523999139434, "count": 1, "is_parallel": true, "self": 0.00023829399651731364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002896490004786756, "count": 1, "is_parallel": true, "self": 0.0002896490004786756 }, "communicator.exchange": { "total": 0.031307631001254776, "count": 1, "is_parallel": true, "self": 0.031307631001254776 }, "steps_from_proto": { "total": 0.000712950000888668, "count": 1, "is_parallel": true, "self": 0.00021224399824859574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005007060026400723, "count": 2, "is_parallel": true, "self": 0.0005007060026400723 } } } } } } }, "UnityEnvironment.step": { "total": 1853.3986743564965, "count": 231968, "is_parallel": true, "self": 58.20990138154957, "children": { "UnityEnvironment._generate_step_input": { "total": 119.30410309381477, "count": 231968, "is_parallel": true, "self": 119.30410309381477 }, "communicator.exchange": { "total": 1537.216502549214, "count": 231968, "is_parallel": true, "self": 1537.216502549214 }, "steps_from_proto": { "total": 138.66816733191808, "count": 231968, "is_parallel": true, "self": 53.93076417197517, "children": { "_process_rank_one_or_two_observation": { "total": 84.73740315994291, "count": 463936, "is_parallel": true, "self": 84.73740315994291 } } } } } } } } } } }, "trainer_advance": { "total": 1739.0692361159781, "count": 231969, "self": 14.493765790077305, "children": { "process_trajectory": { "total": 305.1985729358894, "count": 231969, "self": 302.9912175118916, "children": { "RLTrainer._checkpoint": { "total": 2.2073554239977966, "count": 4, "self": 2.2073554239977966 } } }, "_update_policy": { "total": 1419.3768973900114, "count": 97, "self": 773.1066672531088, "children": { "TorchPPOOptimizer.update": { "total": 646.2702301369027, "count": 2910, "self": 646.2702301369027 } } } } } } }, "trainer_threads": { "total": 2.562999725341797e-06, "count": 1, "self": 2.562999725341797e-06 }, "TrainerController._save_models": { "total": 0.2326871109980857, "count": 1, "self": 0.003496960998745635, "children": { "RLTrainer._checkpoint": { "total": 0.22919014999934006, "count": 1, "self": 0.22919014999934006 } } } } } } }