{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404548168182373, "min": 1.404548168182373, "max": 1.4283303022384644, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69702.109375, "min": 69479.2734375, "max": 78059.546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.60849056603773, "min": 73.0701754385965, "max": 394.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49359.0, "min": 48662.0, "max": 50038.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999937.0, "min": 49497.0, "max": 1999937.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999937.0, "min": 49497.0, "max": 1999937.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4457247257232666, "min": 0.011310546658933163, "max": 2.5358903408050537, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1555.48095703125, "min": 1.4251289367675781, "max": 1734.549072265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8374005292759, "min": 1.9182565957307816, "max": 4.089399206210505, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2440.5867366194725, "min": 241.70033106207848, "max": 2695.6147460341454, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8374005292759, "min": 1.9182565957307816, "max": 4.089399206210505, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2440.5867366194725, "min": 241.70033106207848, "max": 2695.6147460341454, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016602272058662493, "min": 0.014811632278118244, "max": 0.019846152761359308, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04980681617598748, "min": 0.029623264556236487, "max": 0.05800713046337478, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05617684941324922, "min": 0.02339305852850278, "max": 0.06471687679489455, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16853054823974767, "min": 0.04684987136473258, "max": 0.18574739334483942, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.903848698749996e-06, "min": 3.903848698749996e-06, "max": 0.00029533125155625003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1711546096249987e-05, "min": 1.1711546096249987e-05, "max": 0.00084428686857105, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130125, "min": 0.10130125, "max": 0.19844375000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30390375, "min": 0.20773845, "max": 0.58142895, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.493237499999992e-05, "min": 7.493237499999992e-05, "max": 0.004922343124999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022479712499999977, "min": 0.00022479712499999977, "max": 0.014073304605, "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": "1753435371", "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": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753437861" }, "total": 2489.98708954, "count": 1, "self": 0.5338031060000503, "children": { "run_training.setup": { "total": 0.022515256000133377, "count": 1, "self": 0.022515256000133377 }, "TrainerController.start_learning": { "total": 2489.4307711779998, "count": 1, "self": 4.561985415966774, "children": { "TrainerController._reset_env": { "total": 4.043477012000039, "count": 1, "self": 4.043477012000039 }, "TrainerController.advance": { "total": 2480.7184066070326, "count": 233104, "self": 4.925619916285996, "children": { "env_step": { "total": 1987.2538871188212, "count": 233104, "self": 1558.1198193257003, "children": { "SubprocessEnvManager._take_step": { "total": 426.37795754012313, "count": 233104, "self": 15.853140970169761, "children": { "TorchPolicy.evaluate": { "total": 410.5248165699534, "count": 222886, "self": 410.5248165699534 } } }, "workers": { "total": 2.7561102529978143, "count": 233104, "self": 0.0, "children": { "worker_root": { "total": 2482.1576618910326, "count": 233104, "is_parallel": true, "self": 1213.3868869060836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009001010000702081, "count": 1, "is_parallel": true, "self": 0.00023007400000096823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006700270000692399, "count": 2, "is_parallel": true, "self": 0.0006700270000692399 } } }, "UnityEnvironment.step": { "total": 0.02935159699995893, "count": 1, "is_parallel": true, "self": 0.00028836599994974677, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018193500000052154, "count": 1, "is_parallel": true, "self": 0.00018193500000052154 }, "communicator.exchange": { "total": 0.028100767000069027, "count": 1, "is_parallel": true, "self": 0.028100767000069027 }, "steps_from_proto": { "total": 0.0007805289999396336, "count": 1, "is_parallel": true, "self": 0.0003216529999008344, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045887600003879925, "count": 2, "is_parallel": true, "self": 0.00045887600003879925 } } } } } } }, "UnityEnvironment.step": { "total": 1268.770774984949, "count": 233103, "is_parallel": true, "self": 36.62354131887946, "children": { "UnityEnvironment._generate_step_input": { "total": 82.54846202088743, "count": 233103, "is_parallel": true, "self": 82.54846202088743 }, "communicator.exchange": { "total": 1060.97566498603, "count": 233103, "is_parallel": true, "self": 1060.97566498603 }, "steps_from_proto": { "total": 88.62310665915197, "count": 233103, "is_parallel": true, "self": 32.706827480141555, "children": { "_process_rank_one_or_two_observation": { "total": 55.91627917901042, "count": 466206, "is_parallel": true, "self": 55.91627917901042 } } } } } } } } } } }, "trainer_advance": { "total": 488.53889957192564, "count": 233104, "self": 6.687137063834143, "children": { "process_trajectory": { "total": 173.533441807092, "count": 233104, "self": 172.2312014810916, "children": { "RLTrainer._checkpoint": { "total": 1.3022403260004012, "count": 10, "self": 1.3022403260004012 } } }, "_update_policy": { "total": 308.3183207009995, "count": 97, "self": 244.27346191199763, "children": { "TorchPPOOptimizer.update": { "total": 64.04485878900186, "count": 2910, "self": 64.04485878900186 } } } } } } }, "trainer_threads": { "total": 9.919999683916103e-07, "count": 1, "self": 9.919999683916103e-07 }, "TrainerController._save_models": { "total": 0.10690115100032926, "count": 1, "self": 0.0016243690001829236, "children": { "RLTrainer._checkpoint": { "total": 0.10527678200014634, "count": 1, "self": 0.10527678200014634 } } } } } } }