{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4008175134658813, "min": 1.4008175134658813, "max": 1.4265143871307373, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70430.3046875, "min": 68932.203125, "max": 77481.1015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.02622950819672, "min": 73.22814814814815, "max": 372.0148148148148, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49426.0, "min": 49078.0, "max": 50244.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999963.0, "min": 49974.0, "max": 1999963.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999963.0, "min": 49974.0, "max": 1999963.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.477006673812866, "min": 0.03272281587123871, "max": 2.4941799640655518, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1510.9739990234375, "min": 4.384857177734375, "max": 1661.55615234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.838094287524458, "min": 1.8107893156693942, "max": 4.004223267604595, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2341.2375153899193, "min": 242.64576829969883, "max": 2595.0001284480095, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.838094287524458, "min": 1.8107893156693942, "max": 4.004223267604595, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2341.2375153899193, "min": 242.64576829969883, "max": 2595.0001284480095, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01625356175661889, "min": 0.012906617318852415, "max": 0.020312631883037585, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04876068526985666, "min": 0.02581323463770483, "max": 0.05482193987894182, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05837883680231041, "min": 0.023291355154166617, "max": 0.06902599222958088, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17513651040693123, "min": 0.04658271030833323, "max": 0.1938101839274168, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.659348780249992e-06, "min": 3.659348780249992e-06, "max": 0.00029533305155565, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0978046340749975e-05, "min": 1.0978046340749975e-05, "max": 0.000844185018605, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121975, "min": 0.10121975, "max": 0.19844435, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30365925, "min": 0.20757304999999995, "max": 0.5813949999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.086552499999987e-05, "min": 7.086552499999987e-05, "max": 0.004922373064999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021259657499999964, "min": 0.00021259657499999964, "max": 0.0140716105, "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": "1717519324", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717521847" }, "total": 2522.7849823789998, "count": 1, "self": 0.4424682369999573, "children": { "run_training.setup": { "total": 0.08963143399995488, "count": 1, "self": 0.08963143399995488 }, "TrainerController.start_learning": { "total": 2522.252882708, "count": 1, "self": 4.728799125009118, "children": { "TrainerController._reset_env": { "total": 3.519068076999986, "count": 1, "self": 3.519068076999986 }, "TrainerController.advance": { "total": 2513.886661174991, "count": 233309, "self": 5.147190383066118, "children": { "env_step": { "total": 1979.3036186769236, "count": 233309, "self": 1637.612221396996, "children": { "SubprocessEnvManager._take_step": { "total": 338.59135152003023, "count": 233309, "self": 17.222374775016817, "children": { "TorchPolicy.evaluate": { "total": 321.3689767450134, "count": 222998, "self": 321.3689767450134 } } }, "workers": { "total": 3.100045759897455, "count": 233309, "self": 0.0, "children": { "worker_root": { "total": 2514.577642441, "count": 233309, "is_parallel": true, "self": 1196.0680277629544, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011461080000003676, "count": 1, "is_parallel": true, "self": 0.0003437709999616345, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008023370000387331, "count": 2, "is_parallel": true, "self": 0.0008023370000387331 } } }, "UnityEnvironment.step": { "total": 0.028878501999997752, "count": 1, "is_parallel": true, "self": 0.000377347999972244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020510100000592502, "count": 1, "is_parallel": true, "self": 0.00020510100000592502 }, "communicator.exchange": { "total": 0.027558191000025545, "count": 1, "is_parallel": true, "self": 0.027558191000025545 }, "steps_from_proto": { "total": 0.0007378619999940383, "count": 1, "is_parallel": true, "self": 0.00020347399998854598, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005343880000054924, "count": 2, "is_parallel": true, "self": 0.0005343880000054924 } } } } } } }, "UnityEnvironment.step": { "total": 1318.5096146780456, "count": 233308, "is_parallel": true, "self": 41.03291495203848, "children": { "UnityEnvironment._generate_step_input": { "total": 82.45472042306784, "count": 233308, "is_parallel": true, "self": 82.45472042306784 }, "communicator.exchange": { "total": 1099.9978125509606, "count": 233308, "is_parallel": true, "self": 1099.9978125509606 }, "steps_from_proto": { "total": 95.0241667519789, "count": 233308, "is_parallel": true, "self": 33.63961801300104, "children": { "_process_rank_one_or_two_observation": { "total": 61.384548738977855, "count": 466616, "is_parallel": true, "self": 61.384548738977855 } } } } } } } } } } }, "trainer_advance": { "total": 529.4358521150011, "count": 233309, "self": 7.061622838914786, "children": { "process_trajectory": { "total": 162.69287841108792, "count": 233309, "self": 161.15305487108833, "children": { "RLTrainer._checkpoint": { "total": 1.5398235399995883, "count": 10, "self": 1.5398235399995883 } } }, "_update_policy": { "total": 359.6813508649984, "count": 97, "self": 292.5333047730011, "children": { "TorchPPOOptimizer.update": { "total": 67.14804609199734, "count": 2910, "self": 67.14804609199734 } } } } } } }, "trainer_threads": { "total": 1.0250000741507392e-06, "count": 1, "self": 1.0250000741507392e-06 }, "TrainerController._save_models": { "total": 0.11835330599978988, "count": 1, "self": 0.0019063919999098289, "children": { "RLTrainer._checkpoint": { "total": 0.11644691399988005, "count": 1, "self": 0.11644691399988005 } } } } } } }