{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4108299016952515, "min": 1.4108299016952515, "max": 1.4296692609786987, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69549.6796875, "min": 68916.5, "max": 77054.0546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.65524193548387, "min": 94.55172413793103, "max": 430.14529914529913, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49429.0, "min": 48849.0, "max": 50327.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999997.0, "min": 49694.0, "max": 1999997.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999997.0, "min": 49694.0, "max": 1999997.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3438403606414795, "min": 0.19686990976333618, "max": 2.397761821746826, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1162.5447998046875, "min": 22.836910247802734, "max": 1225.123046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6237079052915497, "min": 1.7729845041858738, "max": 3.835285490989685, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1797.3591210246086, "min": 205.66620248556137, "max": 1939.5019221901894, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6237079052915497, "min": 1.7729845041858738, "max": 3.835285490989685, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1797.3591210246086, "min": 205.66620248556137, "max": 1939.5019221901894, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01610530742845084, "min": 0.014893395968526117, "max": 0.019722430750456016, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048315922285352524, "min": 0.029786791937052234, "max": 0.05421178500534249, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.046012497858868705, "min": 0.02069387532149752, "max": 0.07427403322524494, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1380374935766061, "min": 0.04138775064299504, "max": 0.2228220996757348, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.249448916883329e-06, "min": 3.249448916883329e-06, "max": 0.00029537175154275, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.748346750649987e-06, "min": 9.748346750649987e-06, "max": 0.0008440381686539499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108311666666668, "min": 0.10108311666666668, "max": 0.19845725000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30324935000000003, "min": 0.20730135, "max": 0.5813460500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.40475216666666e-05, "min": 6.40475216666666e-05, "max": 0.004923016775000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001921425649999998, "min": 0.0001921425649999998, "max": 0.014069167895000002, "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": "1686584893", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1686587641" }, "total": 2747.95756222, "count": 1, "self": 0.48932695000030435, "children": { "run_training.setup": { "total": 0.055187333000048966, "count": 1, "self": 0.055187333000048966 }, "TrainerController.start_learning": { "total": 2747.4130479369996, "count": 1, "self": 5.525862767147373, "children": { "TrainerController._reset_env": { "total": 5.850046409000015, "count": 1, "self": 5.850046409000015 }, "TrainerController.advance": { "total": 2735.9121867568524, "count": 231444, "self": 5.3741705247202844, "children": { "env_step": { "total": 2145.684519710055, "count": 231444, "self": 1804.0598060968532, "children": { "SubprocessEnvManager._take_step": { "total": 338.2055305711151, "count": 231444, "self": 20.308081131080257, "children": { "TorchPolicy.evaluate": { "total": 317.89744944003485, "count": 222901, "self": 317.89744944003485 } } }, "workers": { "total": 3.4191830420869564, "count": 231444, "self": 0.0, "children": { "worker_root": { "total": 2738.3855896799455, "count": 231444, "is_parallel": true, "self": 1268.0538545837849, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010015710000743638, "count": 1, "is_parallel": true, "self": 0.00027501300007770624, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007265579999966576, "count": 2, "is_parallel": true, "self": 0.0007265579999966576 } } }, "UnityEnvironment.step": { "total": 0.06568472399999337, "count": 1, "is_parallel": true, "self": 0.00037041999985376606, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022231000002648216, "count": 1, "is_parallel": true, "self": 0.00022231000002648216 }, "communicator.exchange": { "total": 0.06403053000008185, "count": 1, "is_parallel": true, "self": 0.06403053000008185 }, "steps_from_proto": { "total": 0.0010614640000312647, "count": 1, "is_parallel": true, "self": 0.00022729700003765174, "children": { "_process_rank_one_or_two_observation": { "total": 0.000834166999993613, "count": 2, "is_parallel": true, "self": 0.000834166999993613 } } } } } } }, "UnityEnvironment.step": { "total": 1470.3317350961606, "count": 231443, "is_parallel": true, "self": 44.876138903026, "children": { "UnityEnvironment._generate_step_input": { "total": 85.91073709015745, "count": 231443, "is_parallel": true, "self": 85.91073709015745 }, "communicator.exchange": { "total": 1231.2715383840005, "count": 231443, "is_parallel": true, "self": 1231.2715383840005 }, "steps_from_proto": { "total": 108.27332071897672, "count": 231443, "is_parallel": true, "self": 37.02485344699994, "children": { "_process_rank_one_or_two_observation": { "total": 71.24846727197678, "count": 462886, "is_parallel": true, "self": 71.24846727197678 } } } } } } } } } } }, "trainer_advance": { "total": 584.853496522077, "count": 231444, "self": 8.668192802143608, "children": { "process_trajectory": { "total": 147.19730723693374, "count": 231444, "self": 145.59585290093264, "children": { "RLTrainer._checkpoint": { "total": 1.6014543360010975, "count": 10, "self": 1.6014543360010975 } } }, "_update_policy": { "total": 428.9879964829996, "count": 97, "self": 363.69844358199646, "children": { "TorchPPOOptimizer.update": { "total": 65.28955290100316, "count": 2910, "self": 65.28955290100316 } } } } } } }, "trainer_threads": { "total": 1.407000127073843e-06, "count": 1, "self": 1.407000127073843e-06 }, "TrainerController._save_models": { "total": 0.12495059699995181, "count": 1, "self": 0.002153124999949796, "children": { "RLTrainer._checkpoint": { "total": 0.12279747200000202, "count": 1, "self": 0.12279747200000202 } } } } } } }