{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3970693349838257, "min": 1.3970624208450317, "max": 1.4273605346679688, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71103.84375, "min": 68994.4453125, "max": 77544.4765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.88646967340591, "min": 71.6759941089838, "max": 404.35483870967744, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49438.0, "min": 48668.0, "max": 50140.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999981.0, "min": 49921.0, "max": 1999981.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999981.0, "min": 49921.0, "max": 1999981.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.529876708984375, "min": 0.049263179302215576, "max": 2.5418813228607178, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1626.710693359375, "min": 6.059370994567871, "max": 1676.0794677734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9007270669862977, "min": 1.860346065546439, "max": 4.009829531783707, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2508.1675040721893, "min": 228.822566062212, "max": 2614.4088547229767, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9007270669862977, "min": 1.860346065546439, "max": 4.009829531783707, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2508.1675040721893, "min": 228.822566062212, "max": 2614.4088547229767, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01577033059729729, "min": 0.013188009662553669, "max": 0.018836015780478495, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04731099179189187, "min": 0.026376019325107337, "max": 0.05631129989924375, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06135362357729011, "min": 0.021839615671585003, "max": 0.0659477765361468, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18406087073187033, "min": 0.043679231343170005, "max": 0.1978433296084404, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.065248644949995e-06, "min": 4.065248644949995e-06, "max": 0.00029536372654542504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2195745934849985e-05, "min": 1.2195745934849985e-05, "max": 0.0008444893685035497, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10135505, "min": 0.10135505, "max": 0.198454575, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30406515, "min": 0.20789585, "max": 0.58149645, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.761699499999994e-05, "min": 7.761699499999994e-05, "max": 0.004922883292499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002328509849999998, "min": 0.0002328509849999998, "max": 0.014076672855, "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": "1672849693", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1672852000" }, "total": 2307.043704233, "count": 1, "self": 0.3906339599993771, "children": { "run_training.setup": { "total": 0.10615941000003204, "count": 1, "self": 0.10615941000003204 }, "TrainerController.start_learning": { "total": 2306.5469108630004, "count": 1, "self": 3.8462015959412383, "children": { "TrainerController._reset_env": { "total": 7.386240528999963, "count": 1, "self": 7.386240528999963 }, "TrainerController.advance": { "total": 2295.189979783059, "count": 233429, "self": 4.07074854703842, "children": { "env_step": { "total": 1821.2316896339328, "count": 233429, "self": 1531.4703649138924, "children": { "SubprocessEnvManager._take_step": { "total": 287.06674520006703, "count": 233429, "self": 14.762443229009023, "children": { "TorchPolicy.evaluate": { "total": 272.304301971058, "count": 223028, "self": 67.77070203305772, "children": { "TorchPolicy.sample_actions": { "total": 204.5335999380003, "count": 223028, "self": 204.5335999380003 } } } } }, "workers": { "total": 2.6945795199732743, "count": 233429, "self": 0.0, "children": { "worker_root": { "total": 2298.4269883060324, "count": 233429, "is_parallel": true, "self": 1037.2276204180212, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029385060000208796, "count": 1, "is_parallel": true, "self": 0.00041227300005175493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025262329999691246, "count": 2, "is_parallel": true, "self": 0.0025262329999691246 } } }, "UnityEnvironment.step": { "total": 0.028739409999957388, "count": 1, "is_parallel": true, "self": 0.00029130399997256973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002044240000032005, "count": 1, "is_parallel": true, "self": 0.0002044240000032005 }, "communicator.exchange": { "total": 0.027510754999980236, "count": 1, "is_parallel": true, "self": 0.027510754999980236 }, "steps_from_proto": { "total": 0.0007329270000013821, "count": 1, "is_parallel": true, "self": 0.00024702600001091923, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004859009999904629, "count": 2, "is_parallel": true, "self": 0.0004859009999904629 } } } } } } }, "UnityEnvironment.step": { "total": 1261.1993678880112, "count": 233428, "is_parallel": true, "self": 35.62272442982021, "children": { "UnityEnvironment._generate_step_input": { "total": 81.96604175502125, "count": 233428, "is_parallel": true, "self": 81.96604175502125 }, "communicator.exchange": { "total": 1045.612217896073, "count": 233428, "is_parallel": true, "self": 1045.612217896073 }, "steps_from_proto": { "total": 97.99838380709679, "count": 233428, "is_parallel": true, "self": 42.56883378702514, "children": { "_process_rank_one_or_two_observation": { "total": 55.429550020071645, "count": 466856, "is_parallel": true, "self": 55.429550020071645 } } } } } } } } } } }, "trainer_advance": { "total": 469.8875416020875, "count": 233429, "self": 6.0881078401608875, "children": { "process_trajectory": { "total": 160.16291442692727, "count": 233429, "self": 158.81456255392754, "children": { "RLTrainer._checkpoint": { "total": 1.3483518729997286, "count": 10, "self": 1.3483518729997286 } } }, "_update_policy": { "total": 303.6365193349993, "count": 97, "self": 251.33814743099617, "children": { "TorchPPOOptimizer.update": { "total": 52.29837190400315, "count": 2910, "self": 52.29837190400315 } } } } } } }, "trainer_threads": { "total": 8.560000424040481e-07, "count": 1, "self": 8.560000424040481e-07 }, "TrainerController._save_models": { "total": 0.12448809900024571, "count": 1, "self": 0.0020294640003157838, "children": { "RLTrainer._checkpoint": { "total": 0.12245863499992993, "count": 1, "self": 0.12245863499992993 } } } } } } }