{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4085406064987183, "min": 1.4085406064987183, "max": 1.428816795349121, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71228.4921875, "min": 68515.859375, "max": 76521.640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.94664371772805, "min": 82.50251256281408, "max": 418.22314049586777, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49354.0, "min": 48886.0, "max": 50605.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999871.0, "min": 49976.0, "max": 1999871.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999871.0, "min": 49976.0, "max": 1999871.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4466769695281982, "min": 0.12547071278095245, "max": 2.456425905227661, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1421.519287109375, "min": 15.056486129760742, "max": 1436.10498046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.92594316894134, "min": 1.853115016222, "max": 3.93763029391545, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2280.9729811549187, "min": 222.37380194664001, "max": 2280.9729811549187, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.92594316894134, "min": 1.853115016222, "max": 3.93763029391545, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2280.9729811549187, "min": 222.37380194664001, "max": 2280.9729811549187, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015900256120625678, "min": 0.013303050400221159, "max": 0.020937448769109322, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04770076836187703, "min": 0.026606100800442317, "max": 0.06129020548348005, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.055334961828258304, "min": 0.022954517385611932, "max": 0.059458933832744754, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1660048854847749, "min": 0.045909034771223864, "max": 0.17025383884708087, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3335988888333334e-06, "min": 3.3335988888333334e-06, "max": 0.000295347226550925, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.00007966665e-05, "min": 1.00007966665e-05, "max": 0.0008440962186346, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111116666666668, "min": 0.10111116666666668, "max": 0.198449075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30333350000000003, "min": 0.2073715, "max": 0.5813654, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.544721666666668e-05, "min": 6.544721666666668e-05, "max": 0.0049226088425, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019634165000000003, "min": 0.00019634165000000003, "max": 0.014070133459999998, "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": "1739956637", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/jim/.local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739959612" }, "total": 2975.4049653330003, "count": 1, "self": 0.7870384289999492, "children": { "run_training.setup": { "total": 0.01795327599393204, "count": 1, "self": 0.01795327599393204 }, "TrainerController.start_learning": { "total": 2974.5999736280064, "count": 1, "self": 4.4614553120482014, "children": { "TrainerController._reset_env": { "total": 2.210790541008464, "count": 1, "self": 2.210790541008464 }, "TrainerController.advance": { "total": 2967.79475110794, "count": 232391, "self": 3.8415069078619126, "children": { "env_step": { "total": 2487.3125556756568, "count": 232391, "self": 1678.1371348125103, "children": { "SubprocessEnvManager._take_step": { "total": 806.1636051644746, "count": 232391, "self": 15.555463049036916, "children": { "TorchPolicy.evaluate": { "total": 790.6081421154377, "count": 222928, "self": 790.6081421154377 } } }, "workers": { "total": 3.011815698671853, "count": 232391, "self": 0.0, "children": { "worker_root": { "total": 2964.1738527944253, "count": 232391, "is_parallel": true, "self": 1522.3254151673173, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012583679927047342, "count": 1, "is_parallel": true, "self": 0.00033650899422354996, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009218589984811842, "count": 2, "is_parallel": true, "self": 0.0009218589984811842 } } }, "UnityEnvironment.step": { "total": 0.020921150004141964, "count": 1, "is_parallel": true, "self": 0.00022084898955654353, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022418600565288216, "count": 1, "is_parallel": true, "self": 0.00022418600565288216 }, "communicator.exchange": { "total": 0.020109429009607993, "count": 1, "is_parallel": true, "self": 0.020109429009607993 }, "steps_from_proto": { "total": 0.00036668599932454526, "count": 1, "is_parallel": true, "self": 9.405800665263087e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002726279926719144, "count": 2, "is_parallel": true, "self": 0.0002726279926719144 } } } } } } }, "UnityEnvironment.step": { "total": 1441.848437627108, "count": 232390, "is_parallel": true, "self": 24.794787576509407, "children": { "UnityEnvironment._generate_step_input": { "total": 47.44057063420769, "count": 232390, "is_parallel": true, "self": 47.44057063420769 }, "communicator.exchange": { "total": 1315.3395575984032, "count": 232390, "is_parallel": true, "self": 1315.3395575984032 }, "steps_from_proto": { "total": 54.273521817987785, "count": 232390, "is_parallel": true, "self": 16.644702604564372, "children": { "_process_rank_one_or_two_observation": { "total": 37.62881921342341, "count": 464780, "is_parallel": true, "self": 37.62881921342341 } } } } } } } } } } }, "trainer_advance": { "total": 476.6406885244214, "count": 232391, "self": 6.787732578319265, "children": { "process_trajectory": { "total": 181.0950156311883, "count": 232391, "self": 179.51645086317149, "children": { "RLTrainer._checkpoint": { "total": 1.578564768016804, "count": 10, "self": 1.578564768016804 } } }, "_update_policy": { "total": 288.75794031491387, "count": 97, "self": 189.35034307236492, "children": { "TorchPPOOptimizer.update": { "total": 99.40759724254895, "count": 2910, "self": 99.40759724254895 } } } } } } }, "trainer_threads": { "total": 7.220078259706497e-07, "count": 1, "self": 7.220078259706497e-07 }, "TrainerController._save_models": { "total": 0.1329759450018173, "count": 1, "self": 0.003921897005056962, "children": { "RLTrainer._checkpoint": { "total": 0.12905404799676035, "count": 1, "self": 0.12905404799676035 } } } } } } }