{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4026321172714233, "min": 1.4026321172714233, "max": 1.4259713888168335, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68946.3828125, "min": 68192.546875, "max": 77701.5859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 117.07459207459208, "min": 81.07704918032788, "max": 405.9756097560976, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50225.0, "min": 48870.0, "max": 50225.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999914.0, "min": 49612.0, "max": 1999914.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999914.0, "min": 49612.0, "max": 1999914.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3227264881134033, "min": 0.10803727805614471, "max": 2.454882860183716, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 996.4496459960938, "min": 13.180547714233398, "max": 1478.5267333984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.571781223609453, "min": 1.7288891728051374, "max": 3.951884832875482, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1532.2941449284554, "min": 210.92447908222675, "max": 2332.0513032078743, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.571781223609453, "min": 1.7288891728051374, "max": 3.951884832875482, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1532.2941449284554, "min": 210.92447908222675, "max": 2332.0513032078743, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016800137617974543, "min": 0.011689487404267614, "max": 0.019669263378212537, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05040041285392363, "min": 0.02337897480853523, "max": 0.05575013653142377, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04312593282924757, "min": 0.02190477711459001, "max": 0.05892520944277446, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.12937779848774272, "min": 0.04380955422918002, "max": 0.1767756283283234, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4835988388333286e-06, "min": 3.4835988388333286e-06, "max": 0.0002953592265469251, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0450796516499985e-05, "min": 1.0450796516499985e-05, "max": 0.0008441194686268499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116116666666668, "min": 0.10116116666666668, "max": 0.19845307499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034835, "min": 0.20749225, "max": 0.5813731499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.794221666666659e-05, "min": 6.794221666666659e-05, "max": 0.004922808442499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020382664999999978, "min": 0.00020382664999999978, "max": 0.014070520185000001, "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": "1712403479", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712406059" }, "total": 2579.861787618, "count": 1, "self": 0.5581504700003279, "children": { "run_training.setup": { "total": 0.05594131700001981, "count": 1, "self": 0.05594131700001981 }, "TrainerController.start_learning": { "total": 2579.247695831, "count": 1, "self": 4.58995701805452, "children": { "TrainerController._reset_env": { "total": 2.7918305659999874, "count": 1, "self": 2.7918305659999874 }, "TrainerController.advance": { "total": 2571.731131371945, "count": 231977, "self": 4.888377167068938, "children": { "env_step": { "total": 2075.565813436958, "count": 231977, "self": 1716.0466295548945, "children": { "SubprocessEnvManager._take_step": { "total": 356.3771888199968, "count": 231977, "self": 17.650967028938624, "children": { "TorchPolicy.evaluate": { "total": 338.72622179105815, "count": 223024, "self": 338.72622179105815 } } }, "workers": { "total": 3.1419950620665986, "count": 231977, "self": 0.0, "children": { "worker_root": { "total": 2571.4235040109897, "count": 231977, "is_parallel": true, "self": 1185.5591476239442, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008695099999727063, "count": 1, "is_parallel": true, "self": 0.00020388699999784876, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006656229999748575, "count": 2, "is_parallel": true, "self": 0.0006656229999748575 } } }, "UnityEnvironment.step": { "total": 0.034003229999996165, "count": 1, "is_parallel": true, "self": 0.00041427900004009643, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027130799998076327, "count": 1, "is_parallel": true, "self": 0.00027130799998076327 }, "communicator.exchange": { "total": 0.032482918999960475, "count": 1, "is_parallel": true, "self": 0.032482918999960475 }, "steps_from_proto": { "total": 0.0008347240000148304, "count": 1, "is_parallel": true, "self": 0.000201372999981686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006333510000331444, "count": 2, "is_parallel": true, "self": 0.0006333510000331444 } } } } } } }, "UnityEnvironment.step": { "total": 1385.8643563870455, "count": 231976, "is_parallel": true, "self": 40.78970382201669, "children": { "UnityEnvironment._generate_step_input": { "total": 89.40980239900841, "count": 231976, "is_parallel": true, "self": 89.40980239900841 }, "communicator.exchange": { "total": 1158.4982168610404, "count": 231976, "is_parallel": true, "self": 1158.4982168610404 }, "steps_from_proto": { "total": 97.16663330498011, "count": 231976, "is_parallel": true, "self": 36.99998066511819, "children": { "_process_rank_one_or_two_observation": { "total": 60.16665263986192, "count": 463952, "is_parallel": true, "self": 60.16665263986192 } } } } } } } } } } }, "trainer_advance": { "total": 491.2769407679184, "count": 231977, "self": 7.202231049966315, "children": { "process_trajectory": { "total": 164.44082368695132, "count": 231977, "self": 162.9806272829506, "children": { "RLTrainer._checkpoint": { "total": 1.460196404000726, "count": 10, "self": 1.460196404000726 } } }, "_update_policy": { "total": 319.63388603100077, "count": 97, "self": 255.97128380699985, "children": { "TorchPPOOptimizer.update": { "total": 63.66260222400092, "count": 2910, "self": 63.66260222400092 } } } } } } }, "trainer_threads": { "total": 1.030000021273736e-06, "count": 1, "self": 1.030000021273736e-06 }, "TrainerController._save_models": { "total": 0.13477584500014927, "count": 1, "self": 0.0025036870001713396, "children": { "RLTrainer._checkpoint": { "total": 0.13227215799997794, "count": 1, "self": 0.13227215799997794 } } } } } } }