{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.355497121810913, "min": 1.355497121810913, "max": 1.4256678819656372, "count": 50 }, "Huggy.Policy.Entropy.sum": { "value": 134489.71875, "min": 133301.484375, "max": 146724.140625, "count": 50 }, "Huggy.Environment.EpisodeLength.mean": { "value": 185.83677298311446, "min": 90.01455868971793, "max": 374.7940074906367, "count": 50 }, "Huggy.Environment.EpisodeLength.sum": { "value": 99051.0, "min": 98413.0, "max": 100191.0, "count": 50 }, "Huggy.Step.mean": { "value": 4999977.0, "min": 99955.0, "max": 4999977.0, "count": 50 }, "Huggy.Step.sum": { "value": 4999977.0, "min": 99955.0, "max": 4999977.0, "count": 50 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.183706045150757, "min": 0.2099350094795227, "max": 2.445831298828125, "count": 50 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1163.915283203125, "min": 55.84271240234375, "max": 2638.7099609375, "count": 50 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.431514164737791, "min": 2.3071830669291935, "max": 3.8346111956370406, "count": 50 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1828.9970498052426, "min": 613.7106958031654, "max": 4173.11915653944, "count": 50 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.431514164737791, "min": 2.3071830669291935, "max": 3.8346111956370406, "count": 50 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1828.9970498052426, "min": 613.7106958031654, "max": 4173.11915653944, "count": 50 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018963013240524258, "min": 0.014114999552354374, "max": 0.020051805406110363, "count": 50 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.09481506620262128, "min": 0.06292688251608827, "max": 0.10025902703055181, "count": 50 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.019165817846854526, "min": 0.018313358686864376, "max": 0.04601486931244532, "count": 50 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09582908923427264, "min": 0.07480395575985312, "max": 0.2300743465622266, "count": 50 }, "Huggy.Policy.LearningRate.mean": { "value": 2.980143006652001e-06, "min": 2.980143006652001e-06, "max": 0.00029691159102946996, "count": 50 }, "Huggy.Policy.LearningRate.sum": { "value": 1.4900715033260006e-05, "min": 1.4900715033260006e-05, "max": 0.0014567535144154999, "count": 50 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10099334799999997, "min": 0.10099334799999997, "max": 0.19897052999999998, "count": 50 }, "Huggy.Policy.Epsilon.sum": { "value": 0.5049667399999999, "min": 0.42803962000000007, "max": 0.9855845, "count": 50 }, "Huggy.Policy.Beta.mean": { "value": 5.9568065200000024e-05, "min": 5.9568065200000024e-05, "max": 0.004948629447000001, "count": 50 }, "Huggy.Policy.Beta.sum": { "value": 0.0002978403260000001, "min": 0.0002978403260000001, "max": 0.02428066655, "count": 50 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1783681350", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --force --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1783688384" }, "total": 7034.372791042, "count": 1, "self": 0.47802481899998384, "children": { "run_training.setup": { "total": 0.02970709200053534, "count": 1, "self": 0.02970709200053534 }, "TrainerController.start_learning": { "total": 7033.865059131, "count": 1, "self": 11.637244423843185, "children": { "TrainerController._reset_env": { "total": 2.3923938500001896, "count": 1, "self": 2.3923938500001896 }, "TrainerController.advance": { "total": 7019.622792437158, "count": 577277, "self": 12.162181566162872, "children": { "env_step": { "total": 5739.8300482121085, "count": 577277, "self": 4541.375168943467, "children": { "SubprocessEnvManager._take_step": { "total": 1191.3489153229639, "count": 577277, "self": 42.048765937131975, "children": { "TorchPolicy.evaluate": { "total": 1149.300149385832, "count": 557107, "self": 1149.300149385832 } } }, "workers": { "total": 7.105963945678013, "count": 577277, "self": 0.0, "children": { "worker_root": { "total": 7002.68074231558, "count": 577277, "is_parallel": true, "self": 3332.2947147325294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009943830000338494, "count": 1, "is_parallel": true, "self": 0.0002733569999691099, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007210260000647395, "count": 2, "is_parallel": true, "self": 0.0007210260000647395 } } }, "UnityEnvironment.step": { "total": 0.031503055000030145, "count": 1, "is_parallel": true, "self": 0.00033075200099119684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020513299932645168, "count": 1, "is_parallel": true, "self": 0.00020513299932645168 }, "communicator.exchange": { "total": 0.03019925599983253, "count": 1, "is_parallel": true, "self": 0.03019925599983253 }, "steps_from_proto": { "total": 0.0007679139998799656, "count": 1, "is_parallel": true, "self": 0.00020147099894529674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005664430009346688, "count": 2, "is_parallel": true, "self": 0.0005664430009346688 } } } } } } }, "UnityEnvironment.step": { "total": 3670.3860275830502, "count": 577276, "is_parallel": true, "self": 101.26812601762504, "children": { "UnityEnvironment._generate_step_input": { "total": 229.6153412585354, "count": 577276, "is_parallel": true, "self": 229.6153412585354 }, "communicator.exchange": { "total": 3102.63434175407, "count": 577276, "is_parallel": true, "self": 3102.63434175407 }, "steps_from_proto": { "total": 236.8682185528196, "count": 577276, "is_parallel": true, "self": 88.58773277233922, "children": { "_process_rank_one_or_two_observation": { "total": 148.28048578048038, "count": 1154552, "is_parallel": true, "self": 148.28048578048038 } } } } } } } } } } }, "trainer_advance": { "total": 1267.6305626588864, "count": 577277, "self": 17.90429196108107, "children": { "process_trajectory": { "total": 404.06600347179756, "count": 577277, "self": 399.13743538680046, "children": { "RLTrainer._checkpoint": { "total": 4.928568084997096, "count": 25, "self": 4.928568084997096 } } }, "_update_policy": { "total": 845.6602672260078, "count": 241, "self": 641.7344017740943, "children": { "TorchPPOOptimizer.update": { "total": 203.92586545191352, "count": 7230, "self": 203.92586545191352 } } } } } } }, "trainer_threads": { "total": 1.2509990483522415e-06, "count": 1, "self": 1.2509990483522415e-06 }, "TrainerController._save_models": { "total": 0.212627168999461, "count": 1, "self": 0.004874778998782858, "children": { "RLTrainer._checkpoint": { "total": 0.20775239000067813, "count": 1, "self": 0.20775239000067813 } } } } } } }