{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4053220748901367, "min": 1.4053220748901367, "max": 1.4298067092895508, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70531.7109375, "min": 68924.5390625, "max": 75597.5234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.893039049236, "min": 80.20779220779221, "max": 421.8655462184874, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49413.0, "min": 48750.0, "max": 50202.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999954.0, "min": 49747.0, "max": 1999954.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999954.0, "min": 49747.0, "max": 1999954.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4512274265289307, "min": 0.034198097884655, "max": 2.4697649478912354, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1443.77294921875, "min": 4.035375595092773, "max": 1487.4339599609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7956992120613267, "min": 1.8274070004285392, "max": 3.967547394362363, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2235.6668359041214, "min": 215.63402605056763, "max": 2360.3057378530502, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7956992120613267, "min": 1.8274070004285392, "max": 3.967547394362363, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2235.6668359041214, "min": 215.63402605056763, "max": 2360.3057378530502, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017430490342020575, "min": 0.013027220501195794, "max": 0.01955503555048684, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05229147102606172, "min": 0.026054441002391588, "max": 0.05777468646798904, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054122948232624264, "min": 0.02317493309577306, "max": 0.06019052287770641, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1623688446978728, "min": 0.04634986619154612, "max": 0.18057156863311924, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.42279885909999e-06, "min": 3.42279885909999e-06, "max": 0.00029526457657847496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.026839657729997e-05, "min": 1.026839657729997e-05, "max": 0.0008439937686687499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114089999999998, "min": 0.10114089999999998, "max": 0.19842152499999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30342269999999993, "min": 0.2074129, "max": 0.5813312500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.693090999999983e-05, "min": 6.693090999999983e-05, "max": 0.0049212340974999986, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002007927299999995, "min": 0.0002007927299999995, "max": 0.014068429375000004, "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": "1719869716", "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": "1719872176" }, "total": 2459.342330957, "count": 1, "self": 0.48762195899962535, "children": { "run_training.setup": { "total": 0.10206052800003818, "count": 1, "self": 0.10206052800003818 }, "TrainerController.start_learning": { "total": 2458.75264847, "count": 1, "self": 4.5427618549110775, "children": { "TrainerController._reset_env": { "total": 3.025661008000043, "count": 1, "self": 3.025661008000043 }, "TrainerController.advance": { "total": 2451.068943935089, "count": 232102, "self": 5.03011138416241, "children": { "env_step": { "total": 1949.2521449499545, "count": 232102, "self": 1603.3846842938835, "children": { "SubprocessEnvManager._take_step": { "total": 342.90903592617155, "count": 232102, "self": 18.244144981314776, "children": { "TorchPolicy.evaluate": { "total": 324.6648909448568, "count": 222882, "self": 324.6648909448568 } } }, "workers": { "total": 2.958424729899434, "count": 232102, "self": 0.0, "children": { "worker_root": { "total": 2451.6412814491014, "count": 232102, "is_parallel": true, "self": 1165.3580822059384, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008826279999993858, "count": 1, "is_parallel": true, "self": 0.0002195849999679922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006630430000313936, "count": 2, "is_parallel": true, "self": 0.0006630430000313936 } } }, "UnityEnvironment.step": { "total": 0.030234844999995403, "count": 1, "is_parallel": true, "self": 0.0003682519998164935, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001548960001400701, "count": 1, "is_parallel": true, "self": 0.0001548960001400701 }, "communicator.exchange": { "total": 0.028933738999967318, "count": 1, "is_parallel": true, "self": 0.028933738999967318 }, "steps_from_proto": { "total": 0.0007779580000715214, "count": 1, "is_parallel": true, "self": 0.0002173470002162503, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005606109998552711, "count": 2, "is_parallel": true, "self": 0.0005606109998552711 } } } } } } }, "UnityEnvironment.step": { "total": 1286.283199243163, "count": 232101, "is_parallel": true, "self": 39.774061257987114, "children": { "UnityEnvironment._generate_step_input": { "total": 85.04062283316898, "count": 232101, "is_parallel": true, "self": 85.04062283316898 }, "communicator.exchange": { "total": 1069.8603678870334, "count": 232101, "is_parallel": true, "self": 1069.8603678870334 }, "steps_from_proto": { "total": 91.60814726497347, "count": 232101, "is_parallel": true, "self": 34.286285709911226, "children": { "_process_rank_one_or_two_observation": { "total": 57.32186155506224, "count": 464202, "is_parallel": true, "self": 57.32186155506224 } } } } } } } } } } }, "trainer_advance": { "total": 496.7866876009723, "count": 232102, "self": 6.614710190958931, "children": { "process_trajectory": { "total": 157.7609594700118, "count": 232102, "self": 156.23560917201212, "children": { "RLTrainer._checkpoint": { "total": 1.5253502979996938, "count": 10, "self": 1.5253502979996938 } } }, "_update_policy": { "total": 332.41101794000156, "count": 97, "self": 267.81751320498256, "children": { "TorchPPOOptimizer.update": { "total": 64.593504735019, "count": 2910, "self": 64.593504735019 } } } } } } }, "trainer_threads": { "total": 9.890000001178123e-07, "count": 1, "self": 9.890000001178123e-07 }, "TrainerController._save_models": { "total": 0.11528068300003724, "count": 1, "self": 0.0019522259999575908, "children": { "RLTrainer._checkpoint": { "total": 0.11332845700007965, "count": 1, "self": 0.11332845700007965 } } } } } } }