{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4031269550323486, "min": 1.4031269550323486, "max": 1.4270142316818237, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69724.1875, "min": 67396.9921875, "max": 79785.0078125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.99088145896657, "min": 72.48823529411764, "max": 388.7421875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49344.0, "min": 49281.0, "max": 50329.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49882.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49882.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.429810047149658, "min": 0.06919645518064499, "max": 2.534355401992798, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1598.81494140625, "min": 9.341521263122559, "max": 1650.199951171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.741642819258942, "min": 1.6569878626752783, "max": 4.088955957658829, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2462.000975072384, "min": 223.69336146116257, "max": 2646.7351167798042, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.741642819258942, "min": 1.6569878626752783, "max": 4.088955957658829, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2462.000975072384, "min": 223.69336146116257, "max": 2646.7351167798042, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017103854105597647, "min": 0.013916357679651506, "max": 0.02093486476417941, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051311562316792944, "min": 0.028354479445260948, "max": 0.056769841733087856, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06339871436357498, "min": 0.02224176445355018, "max": 0.06971474699676036, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19019614309072494, "min": 0.04448352890710036, "max": 0.19044515726466976, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.990548669850002e-06, "min": 3.990548669850002e-06, "max": 0.00029534205155265, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1971646009550007e-05, "min": 1.1971646009550007e-05, "max": 0.0008439705186765001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10133015000000001, "min": 0.10133015000000001, "max": 0.19844735000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30399045, "min": 0.2077893, "max": 0.5813235, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.637448500000001e-05, "min": 7.637448500000001e-05, "max": 0.004922522765000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022912345500000005, "min": 0.00022912345500000005, "max": 0.014068042650000003, "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": "1692597957", "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": "1692600493" }, "total": 2536.3151510609996, "count": 1, "self": 0.43771095800002513, "children": { "run_training.setup": { "total": 0.04254171100001258, "count": 1, "self": 0.04254171100001258 }, "TrainerController.start_learning": { "total": 2535.8348983919996, "count": 1, "self": 4.593474422063082, "children": { "TrainerController._reset_env": { "total": 4.254801568999994, "count": 1, "self": 4.254801568999994 }, "TrainerController.advance": { "total": 2526.8593329349364, "count": 233369, "self": 4.696786816910844, "children": { "env_step": { "total": 1943.9045177690002, "count": 233369, "self": 1641.8523357219904, "children": { "SubprocessEnvManager._take_step": { "total": 298.97099072493455, "count": 233369, "self": 17.181103891992166, "children": { "TorchPolicy.evaluate": { "total": 281.7898868329424, "count": 222969, "self": 281.7898868329424 } } }, "workers": { "total": 3.0811913220753695, "count": 233369, "self": 0.0, "children": { "worker_root": { "total": 2528.2312179569667, "count": 233369, "is_parallel": true, "self": 1191.2428575929855, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008549980000225332, "count": 1, "is_parallel": true, "self": 0.00021994900004074225, "children": { "_process_rank_one_or_two_observation": { "total": 0.000635048999981791, "count": 2, "is_parallel": true, "self": 0.000635048999981791 } } }, "UnityEnvironment.step": { "total": 0.031055167000033634, "count": 1, "is_parallel": true, "self": 0.0003132340000320255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021759200001270074, "count": 1, "is_parallel": true, "self": 0.00021759200001270074 }, "communicator.exchange": { "total": 0.02968105799999421, "count": 1, "is_parallel": true, "self": 0.02968105799999421 }, "steps_from_proto": { "total": 0.0008432829999946989, "count": 1, "is_parallel": true, "self": 0.00022616600000446851, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006171169999902304, "count": 2, "is_parallel": true, "self": 0.0006171169999902304 } } } } } } }, "UnityEnvironment.step": { "total": 1336.9883603639812, "count": 233368, "is_parallel": true, "self": 40.307256812026935, "children": { "UnityEnvironment._generate_step_input": { "total": 81.57026382297431, "count": 233368, "is_parallel": true, "self": 81.57026382297431 }, "communicator.exchange": { "total": 1115.4213561209322, "count": 233368, "is_parallel": true, "self": 1115.4213561209322 }, "steps_from_proto": { "total": 99.68948360804774, "count": 233368, "is_parallel": true, "self": 35.4182236580931, "children": { "_process_rank_one_or_two_observation": { "total": 64.27125994995464, "count": 466736, "is_parallel": true, "self": 64.27125994995464 } } } } } } } } } } }, "trainer_advance": { "total": 578.2580283490254, "count": 233369, "self": 6.9331971059841635, "children": { "process_trajectory": { "total": 151.0393297340416, "count": 233369, "self": 149.52457312004213, "children": { "RLTrainer._checkpoint": { "total": 1.5147566139994524, "count": 10, "self": 1.5147566139994524 } } }, "_update_policy": { "total": 420.28550150899963, "count": 97, "self": 359.19810729100664, "children": { "TorchPPOOptimizer.update": { "total": 61.087394217992994, "count": 2910, "self": 61.087394217992994 } } } } } } }, "trainer_threads": { "total": 1.0560002010606695e-06, "count": 1, "self": 1.0560002010606695e-06 }, "TrainerController._save_models": { "total": 0.12728840999989188, "count": 1, "self": 0.0020512950000011188, "children": { "RLTrainer._checkpoint": { "total": 0.12523711499989076, "count": 1, "self": 0.12523711499989076 } } } } } } }