{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4070955514907837, "min": 1.4070955514907837, "max": 1.4283969402313232, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68618.421875, "min": 68575.65625, "max": 76677.5234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 108.78384279475982, "min": 79.10576923076923, "max": 417.94166666666666, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49823.0, "min": 48919.0, "max": 50164.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999560.0, "min": 49598.0, "max": 1999560.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999560.0, "min": 49598.0, "max": 1999560.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4012339115142822, "min": 0.11218871921300888, "max": 2.4295125007629395, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1099.76513671875, "min": 13.350457191467285, "max": 1495.4312744140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.704595258272371, "min": 1.8907418524016852, "max": 4.0013418420185225, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1696.7046282887459, "min": 224.99828043580055, "max": 2403.972956776619, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.704595258272371, "min": 1.8907418524016852, "max": 4.0013418420185225, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1696.7046282887459, "min": 224.99828043580055, "max": 2403.972956776619, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01584916488742844, "min": 0.012215512344846502, "max": 0.02053426407510415, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03169832977485688, "min": 0.024431024689693003, "max": 0.05769629075463551, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.046924368912974995, "min": 0.021405481516073147, "max": 0.06768123432993889, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09384873782594999, "min": 0.04281096303214629, "max": 0.18756288836399715, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.595948468049996e-06, "min": 4.595948468049996e-06, "max": 0.00029529375156875, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.191896936099991e-06, "min": 9.191896936099991e-06, "max": 0.0008436975187674999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10153195000000001, "min": 0.10153195000000001, "max": 0.19843125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20306390000000002, "min": 0.20306390000000002, "max": 0.5812325000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.644430499999996e-05, "min": 8.644430499999996e-05, "max": 0.0049217193749999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017288860999999992, "min": 0.00017288860999999992, "max": 0.014063501749999999, "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": "1712556548", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712558961" }, "total": 2413.756272207, "count": 1, "self": 0.48881168000025355, "children": { "run_training.setup": { "total": 0.0561552170000823, "count": 1, "self": 0.0561552170000823 }, "TrainerController.start_learning": { "total": 2413.2113053099997, "count": 1, "self": 4.283452392967774, "children": { "TrainerController._reset_env": { "total": 3.2869751480000104, "count": 1, "self": 3.2869751480000104 }, "TrainerController.advance": { "total": 2405.5169682070323, "count": 232250, "self": 4.634222574030446, "children": { "env_step": { "total": 1915.4722422519862, "count": 232250, "self": 1588.5701700709137, "children": { "SubprocessEnvManager._take_step": { "total": 324.02425772602714, "count": 232250, "self": 17.215036030971646, "children": { "TorchPolicy.evaluate": { "total": 306.8092216950555, "count": 222904, "self": 306.8092216950555 } } }, "workers": { "total": 2.8778144550453817, "count": 232250, "self": 0.0, "children": { "worker_root": { "total": 2405.9782090489334, "count": 232250, "is_parallel": true, "self": 1122.7305808518859, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009159579999504786, "count": 1, "is_parallel": true, "self": 0.0002560299999458948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006599280000045837, "count": 2, "is_parallel": true, "self": 0.0006599280000045837 } } }, "UnityEnvironment.step": { "total": 0.048883398999919336, "count": 1, "is_parallel": true, "self": 0.0033371979999401447, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021700799993595865, "count": 1, "is_parallel": true, "self": 0.00021700799993595865 }, "communicator.exchange": { "total": 0.044425743000033435, "count": 1, "is_parallel": true, "self": 0.044425743000033435 }, "steps_from_proto": { "total": 0.0009034500000097978, "count": 1, "is_parallel": true, "self": 0.00024101600001813495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006624339999916629, "count": 2, "is_parallel": true, "self": 0.0006624339999916629 } } } } } } }, "UnityEnvironment.step": { "total": 1283.2476281970476, "count": 232249, "is_parallel": true, "self": 39.836820990941305, "children": { "UnityEnvironment._generate_step_input": { "total": 83.0163324169996, "count": 232249, "is_parallel": true, "self": 83.0163324169996 }, "communicator.exchange": { "total": 1069.1432710909953, "count": 232249, "is_parallel": true, "self": 1069.1432710909953 }, "steps_from_proto": { "total": 91.25120369811123, "count": 232249, "is_parallel": true, "self": 32.75669340108186, "children": { "_process_rank_one_or_two_observation": { "total": 58.494510297029365, "count": 464498, "is_parallel": true, "self": 58.494510297029365 } } } } } } } } } } }, "trainer_advance": { "total": 485.4105033810158, "count": 232250, "self": 6.7493272340892645, "children": { "process_trajectory": { "total": 154.25659691392764, "count": 232250, "self": 152.91406903592804, "children": { "RLTrainer._checkpoint": { "total": 1.3425278779996006, "count": 10, "self": 1.3425278779996006 } } }, "_update_policy": { "total": 324.4045792329989, "count": 96, "self": 260.6127662010125, "children": { "TorchPPOOptimizer.update": { "total": 63.79181303198641, "count": 2880, "self": 63.79181303198641 } } } } } } }, "trainer_threads": { "total": 8.590000106778461e-07, "count": 1, "self": 8.590000106778461e-07 }, "TrainerController._save_models": { "total": 0.12390870299987, "count": 1, "self": 0.002266916999815294, "children": { "RLTrainer._checkpoint": { "total": 0.12164178600005471, "count": 1, "self": 0.12164178600005471 } } } } } } }