{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4063745737075806, "min": 1.4063745737075806, "max": 1.4283442497253418, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70583.125, "min": 68088.3203125, "max": 77922.78125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.42830188679245, "min": 85.62975778546713, "max": 361.45323741007195, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48987.0, "min": 48919.0, "max": 50242.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49631.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49631.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.364187717437744, "min": 0.11931373924016953, "max": 2.463958740234375, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1253.01953125, "min": 16.465295791625977, "max": 1365.5419921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5802218891539663, "min": 1.7672343191461286, "max": 3.9659530431321524, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1897.5176012516022, "min": 243.87833604216576, "max": 2156.4057800769806, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5802218891539663, "min": 1.7672343191461286, "max": 3.9659530431321524, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1897.5176012516022, "min": 243.87833604216576, "max": 2156.4057800769806, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014935311320409206, "min": 0.012949352296648916, "max": 0.019665569811250963, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04480593396122762, "min": 0.025898704593297833, "max": 0.05899670943375289, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05536888382501073, "min": 0.021772867999970913, "max": 0.0569935085458888, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16610665147503217, "min": 0.043545735999941826, "max": 0.1709805256376664, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2685489105166667e-06, "min": 3.2685489105166667e-06, "max": 0.000295370476543175, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.80564673155e-06, "min": 9.80564673155e-06, "max": 0.0008443389185536999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1010894833333333, "min": 0.1010894833333333, "max": 0.19845682500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032684499999999, "min": 0.20732779999999998, "max": 0.5814463, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.436521833333334e-05, "min": 6.436521833333334e-05, "max": 0.004922995567500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019309565500000002, "min": 0.00019309565500000002, "max": 0.01407417037, "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": "1671235309", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671237666" }, "total": 2357.13801927, "count": 1, "self": 0.3960645829997702, "children": { "run_training.setup": { "total": 0.10805261999996674, "count": 1, "self": 0.10805261999996674 }, "TrainerController.start_learning": { "total": 2356.6339020670002, "count": 1, "self": 4.026731225897038, "children": { "TrainerController._reset_env": { "total": 8.670285944999932, "count": 1, "self": 8.670285944999932 }, "TrainerController.advance": { "total": 2343.817243637103, "count": 232229, "self": 4.41872043017338, "children": { "env_step": { "total": 1856.9766943389493, "count": 232229, "self": 1561.5113232908907, "children": { "SubprocessEnvManager._take_step": { "total": 292.7262306460228, "count": 232229, "self": 14.988549118990363, "children": { "TorchPolicy.evaluate": { "total": 277.73768152703246, "count": 223031, "self": 69.59991880304813, "children": { "TorchPolicy.sample_actions": { "total": 208.13776272398434, "count": 223031, "self": 208.13776272398434 } } } } }, "workers": { "total": 2.7391404020359005, "count": 232229, "self": 0.0, "children": { "worker_root": { "total": 2348.469596485064, "count": 232229, "is_parallel": true, "self": 1063.4148527820398, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002198398000018642, "count": 1, "is_parallel": true, "self": 0.0003344879999076511, "children": { "_process_rank_one_or_two_observation": { "total": 0.001863910000110991, "count": 2, "is_parallel": true, "self": 0.001863910000110991 } } }, "UnityEnvironment.step": { "total": 0.02933819500003665, "count": 1, "is_parallel": true, "self": 0.0002795780000042214, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001843400000325346, "count": 1, "is_parallel": true, "self": 0.0001843400000325346 }, "communicator.exchange": { "total": 0.028169780999974137, "count": 1, "is_parallel": true, "self": 0.028169780999974137 }, "steps_from_proto": { "total": 0.0007044960000257561, "count": 1, "is_parallel": true, "self": 0.00023714000008112635, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046735599994462973, "count": 2, "is_parallel": true, "self": 0.00046735599994462973 } } } } } } }, "UnityEnvironment.step": { "total": 1285.054743703024, "count": 232228, "is_parallel": true, "self": 36.18346893708235, "children": { "UnityEnvironment._generate_step_input": { "total": 84.43722834195069, "count": 232228, "is_parallel": true, "self": 84.43722834195069 }, "communicator.exchange": { "total": 1064.4543991749651, "count": 232228, "is_parallel": true, "self": 1064.4543991749651 }, "steps_from_proto": { "total": 99.9796472490259, "count": 232228, "is_parallel": true, "self": 43.54019355314756, "children": { "_process_rank_one_or_two_observation": { "total": 56.43945369587834, "count": 464456, "is_parallel": true, "self": 56.43945369587834 } } } } } } } } } } }, "trainer_advance": { "total": 482.42182886798, "count": 232229, "self": 6.251811295051311, "children": { "process_trajectory": { "total": 158.84119919592763, "count": 232229, "self": 157.65370497092806, "children": { "RLTrainer._checkpoint": { "total": 1.1874942249995684, "count": 10, "self": 1.1874942249995684 } } }, "_update_policy": { "total": 317.3288183770011, "count": 97, "self": 263.8422246350076, "children": { "TorchPPOOptimizer.update": { "total": 53.48659374199349, "count": 2910, "self": 53.48659374199349 } } } } } } }, "trainer_threads": { "total": 1.3140002010914031e-06, "count": 1, "self": 1.3140002010914031e-06 }, "TrainerController._save_models": { "total": 0.11963994500001718, "count": 1, "self": 0.002499770000213175, "children": { "RLTrainer._checkpoint": { "total": 0.117140174999804, "count": 1, "self": 0.117140174999804 } } } } } } }