{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.412164330482483, "min": 1.412164330482483, "max": 1.4292412996292114, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71071.40625, "min": 68840.0234375, "max": 76024.0078125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.50267379679144, "min": 74.595166163142, "max": 392.5703125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49650.0, "min": 49116.0, "max": 50249.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999550.0, "min": 49627.0, "max": 1999550.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999550.0, "min": 49627.0, "max": 1999550.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.492094039916992, "min": 0.11599651724100113, "max": 2.5015101432800293, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1398.0648193359375, "min": 14.731557846069336, "max": 1581.7637939453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.915841152536253, "min": 1.6224271584683516, "max": 4.019113418181317, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2196.786886572838, "min": 206.04824912548065, "max": 2516.231682598591, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.915841152536253, "min": 1.6224271584683516, "max": 4.019113418181317, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2196.786886572838, "min": 206.04824912548065, "max": 2516.231682598591, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016131253212855277, "min": 0.01367040878564391, "max": 0.019430527271470054, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04839375963856583, "min": 0.02734081757128782, "max": 0.05471378466657674, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05368059612810611, "min": 0.02172153008480867, "max": 0.06370971109718085, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16104178838431835, "min": 0.04344306016961734, "max": 0.17953787085910639, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7213987595666607e-06, "min": 3.7213987595666607e-06, "max": 0.0002952578265807249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1164196278699982e-05, "min": 1.1164196278699982e-05, "max": 0.0008437258687580499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124043333333332, "min": 0.10124043333333332, "max": 0.198419275, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30372129999999997, "min": 0.20761205, "max": 0.58124195, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.189762333333323e-05, "min": 7.189762333333323e-05, "max": 0.004921121822499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002156928699999997, "min": 0.0002156928699999997, "max": 0.014063973305000001, "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": "1696372338", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696375076" }, "total": 2738.5974846589997, "count": 1, "self": 0.6520333789999313, "children": { "run_training.setup": { "total": 0.04621227699999508, "count": 1, "self": 0.04621227699999508 }, "TrainerController.start_learning": { "total": 2737.899239003, "count": 1, "self": 5.697566584912238, "children": { "TrainerController._reset_env": { "total": 4.961590942999919, "count": 1, "self": 4.961590942999919 }, "TrainerController.advance": { "total": 2727.0471561200875, "count": 232901, "self": 5.4297413850890734, "children": { "env_step": { "total": 2120.445705215049, "count": 232901, "self": 1790.1744288901482, "children": { "SubprocessEnvManager._take_step": { "total": 326.7541139720647, "count": 232901, "self": 18.96981683612603, "children": { "TorchPolicy.evaluate": { "total": 307.7842971359387, "count": 222965, "self": 307.7842971359387 } } }, "workers": { "total": 3.5171623528362943, "count": 232901, "self": 0.0, "children": { "worker_root": { "total": 2728.92335375809, "count": 232901, "is_parallel": true, "self": 1274.4535648080623, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010511299999507173, "count": 1, "is_parallel": true, "self": 0.00027005799984181067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007810720001089066, "count": 2, "is_parallel": true, "self": 0.0007810720001089066 } } }, "UnityEnvironment.step": { "total": 0.07142113600002631, "count": 1, "is_parallel": true, "self": 0.00035668400005306466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024111499988066498, "count": 1, "is_parallel": true, "self": 0.00024111499988066498 }, "communicator.exchange": { "total": 0.07005009900012737, "count": 1, "is_parallel": true, "self": 0.07005009900012737 }, "steps_from_proto": { "total": 0.0007732379999652039, "count": 1, "is_parallel": true, "self": 0.00021773599996777193, "children": { "_process_rank_one_or_two_observation": { "total": 0.000555501999997432, "count": 2, "is_parallel": true, "self": 0.000555501999997432 } } } } } } }, "UnityEnvironment.step": { "total": 1454.4697889500276, "count": 232900, "is_parallel": true, "self": 43.37937719689171, "children": { "UnityEnvironment._generate_step_input": { "total": 90.26652240001522, "count": 232900, "is_parallel": true, "self": 90.26652240001522 }, "communicator.exchange": { "total": 1211.1433465820926, "count": 232900, "is_parallel": true, "self": 1211.1433465820926 }, "steps_from_proto": { "total": 109.68054277102806, "count": 232900, "is_parallel": true, "self": 40.336668952217224, "children": { "_process_rank_one_or_two_observation": { "total": 69.34387381881083, "count": 465800, "is_parallel": true, "self": 69.34387381881083 } } } } } } } } } } }, "trainer_advance": { "total": 601.171709519949, "count": 232901, "self": 7.853145508019679, "children": { "process_trajectory": { "total": 156.5540225119289, "count": 232901, "self": 155.09883992692858, "children": { "RLTrainer._checkpoint": { "total": 1.4551825850003297, "count": 10, "self": 1.4551825850003297 } } }, "_update_policy": { "total": 436.7645415000004, "count": 97, "self": 372.892502222993, "children": { "TorchPPOOptimizer.update": { "total": 63.87203927700739, "count": 2910, "self": 63.87203927700739 } } } } } } }, "trainer_threads": { "total": 1.4570000530511606e-06, "count": 1, "self": 1.4570000530511606e-06 }, "TrainerController._save_models": { "total": 0.19292389800011733, "count": 1, "self": 0.0027046119998885843, "children": { "RLTrainer._checkpoint": { "total": 0.19021928600022875, "count": 1, "self": 0.19021928600022875 } } } } } } }