{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4047877788543701, "min": 1.4047877788543701, "max": 1.4283558130264282, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69608.640625, "min": 68954.59375, "max": 76476.140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.85770750988142, "min": 83.24787775891342, "max": 388.09302325581393, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49516.0, "min": 48935.0, "max": 50229.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49930.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49930.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.335214853286743, "min": 0.1655503809452057, "max": 2.4469475746154785, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1181.6187744140625, "min": 21.190448760986328, "max": 1388.9501953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6150725412038947, "min": 1.9621471593854949, "max": 3.969903435643393, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1829.2267058491707, "min": 251.15483640134335, "max": 2229.827545642853, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6150725412038947, "min": 1.9621471593854949, "max": 3.969903435643393, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1829.2267058491707, "min": 251.15483640134335, "max": 2229.827545642853, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016941310307114085, "min": 0.01172654463419652, "max": 0.019718439256272785, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03388262061422817, "min": 0.02345308926839304, "max": 0.0562184489123562, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05575885226329168, "min": 0.021214290708303454, "max": 0.06328591853380203, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.11151770452658336, "min": 0.04242858141660691, "max": 0.18985775560140608, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.519598493499997e-06, "min": 4.519598493499997e-06, "max": 0.00029529697656767494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.039196986999994e-06, "min": 9.039196986999994e-06, "max": 0.0008438592187135998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10150649999999999, "min": 0.10150649999999999, "max": 0.19843232499999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20301299999999997, "min": 0.20301299999999997, "max": 0.5812864, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.517434999999996e-05, "min": 8.517434999999996e-05, "max": 0.004921773017500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017034869999999993, "min": 0.00017034869999999993, "max": 0.014066191360000002, "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": "1753205102", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753207550" }, "total": 2447.621907947, "count": 1, "self": 0.7402337240000634, "children": { "run_training.setup": { "total": 0.02233284999999796, "count": 1, "self": 0.02233284999999796 }, "TrainerController.start_learning": { "total": 2446.859341373, "count": 1, "self": 4.006241311116355, "children": { "TrainerController._reset_env": { "total": 3.2335361450000164, "count": 1, "self": 3.2335361450000164 }, "TrainerController.advance": { "total": 2439.471857923884, "count": 231607, "self": 4.302735908917384, "children": { "env_step": { "total": 1934.9187502729633, "count": 231607, "self": 1525.29201793207, "children": { "SubprocessEnvManager._take_step": { "total": 407.0425402190067, "count": 231607, "self": 14.905388024906642, "children": { "TorchPolicy.evaluate": { "total": 392.13715219410005, "count": 222930, "self": 392.13715219410005 } } }, "workers": { "total": 2.5841921218866446, "count": 231607, "self": 0.0, "children": { "worker_root": { "total": 2439.2184034301195, "count": 231607, "is_parallel": true, "self": 1192.0163676962075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000878904000046532, "count": 1, "is_parallel": true, "self": 0.000280904000078408, "children": { "_process_rank_one_or_two_observation": { "total": 0.000597999999968124, "count": 2, "is_parallel": true, "self": 0.000597999999968124 } } }, "UnityEnvironment.step": { "total": 0.05951947100004418, "count": 1, "is_parallel": true, "self": 0.0003166199999213859, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002249940000638162, "count": 1, "is_parallel": true, "self": 0.0002249940000638162 }, "communicator.exchange": { "total": 0.05829615000004651, "count": 1, "is_parallel": true, "self": 0.05829615000004651 }, "steps_from_proto": { "total": 0.0006817070000124659, "count": 1, "is_parallel": true, "self": 0.0001932060000626734, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004885009999497925, "count": 2, "is_parallel": true, "self": 0.0004885009999497925 } } } } } } }, "UnityEnvironment.step": { "total": 1247.202035733912, "count": 231606, "is_parallel": true, "self": 37.10982911492738, "children": { "UnityEnvironment._generate_step_input": { "total": 82.64774949998218, "count": 231606, "is_parallel": true, "self": 82.64774949998218 }, "communicator.exchange": { "total": 1039.9972380890565, "count": 231606, "is_parallel": true, "self": 1039.9972380890565 }, "steps_from_proto": { "total": 87.44721902994581, "count": 231606, "is_parallel": true, "self": 32.49030565393332, "children": { "_process_rank_one_or_two_observation": { "total": 54.956913376012494, "count": 463212, "is_parallel": true, "self": 54.956913376012494 } } } } } } } } } } }, "trainer_advance": { "total": 500.25037174200304, "count": 231607, "self": 6.123284566009829, "children": { "process_trajectory": { "total": 152.37282939999216, "count": 231607, "self": 151.13810246399237, "children": { "RLTrainer._checkpoint": { "total": 1.2347269359997881, "count": 10, "self": 1.2347269359997881 } } }, "_update_policy": { "total": 341.75425777600105, "count": 96, "self": 277.92382037999266, "children": { "TorchPPOOptimizer.update": { "total": 63.83043739600839, "count": 2880, "self": 63.83043739600839 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.1477050099997541, "count": 1, "self": 0.002413749999504944, "children": { "RLTrainer._checkpoint": { "total": 0.14529126000024917, "count": 1, "self": 0.14529126000024917 } } } } } } }