{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403942346572876, "min": 1.403942346572876, "max": 1.4276233911514282, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70069.359375, "min": 68293.734375, "max": 76734.046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.08098591549296, "min": 78.83225806451613, "max": 390.265625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49462.0, "min": 48876.0, "max": 50279.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999964.0, "min": 49918.0, "max": 1999964.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999964.0, "min": 49918.0, "max": 1999964.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.486104965209961, "min": 0.03290686011314392, "max": 2.536184072494507, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1414.59375, "min": 4.179171085357666, "max": 1580.042724609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.91006789381349, "min": 1.7694620720044834, "max": 4.111282564839747, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2224.828631579876, "min": 224.7216831445694, "max": 2464.7558873295784, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.91006789381349, "min": 1.7694620720044834, "max": 4.111282564839747, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2224.828631579876, "min": 224.7216831445694, "max": 2464.7558873295784, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016067332672097714, "min": 0.013670459159766323, "max": 0.022023540537338702, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04820199801629314, "min": 0.028795327688567338, "max": 0.054714855254375534, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054520343989133836, "min": 0.022041404154151678, "max": 0.06398116492976745, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16356103196740152, "min": 0.044082808308303356, "max": 0.18583753195901714, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.0053986649000005e-06, "min": 4.0053986649000005e-06, "max": 0.0002953359015546999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2016195994700002e-05, "min": 1.2016195994700002e-05, "max": 0.0008443327685557498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10133510000000005, "min": 0.10133510000000005, "max": 0.1984453, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30400530000000014, "min": 0.2078026, "max": 0.58144425, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.662149000000002e-05, "min": 7.662149000000002e-05, "max": 0.004922420470000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022986447000000005, "min": 0.00022986447000000005, "max": 0.014074068075000001, "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": "1693406213", "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": "1693408725" }, "total": 2511.6885852389996, "count": 1, "self": 0.7894735129993933, "children": { "run_training.setup": { "total": 0.04380855199997313, "count": 1, "self": 0.04380855199997313 }, "TrainerController.start_learning": { "total": 2510.8553031740003, "count": 1, "self": 4.559643605992733, "children": { "TrainerController._reset_env": { "total": 4.068265990999976, "count": 1, "self": 4.068265990999976 }, "TrainerController.advance": { "total": 2502.0429055710074, "count": 232695, "self": 4.813042971937648, "children": { "env_step": { "total": 1944.2111782960149, "count": 232695, "self": 1642.674230745135, "children": { "SubprocessEnvManager._take_step": { "total": 298.5289686199522, "count": 232695, "self": 17.47633119793562, "children": { "TorchPolicy.evaluate": { "total": 281.0526374220166, "count": 222953, "self": 281.0526374220166 } } }, "workers": { "total": 3.0079789309276066, "count": 232695, "self": 0.0, "children": { "worker_root": { "total": 2502.87427295808, "count": 232695, "is_parallel": true, "self": 1168.5959717519668, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009642869999879622, "count": 1, "is_parallel": true, "self": 0.00027647599995361816, "children": { "_process_rank_one_or_two_observation": { "total": 0.000687811000034344, "count": 2, "is_parallel": true, "self": 0.000687811000034344 } } }, "UnityEnvironment.step": { "total": 0.03027887399997553, "count": 1, "is_parallel": true, "self": 0.0003583139999818741, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021796099997573037, "count": 1, "is_parallel": true, "self": 0.00021796099997573037 }, "communicator.exchange": { "total": 0.028946216000008462, "count": 1, "is_parallel": true, "self": 0.028946216000008462 }, "steps_from_proto": { "total": 0.000756383000009464, "count": 1, "is_parallel": true, "self": 0.00020155500004648275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005548279999629813, "count": 2, "is_parallel": true, "self": 0.0005548279999629813 } } } } } } }, "UnityEnvironment.step": { "total": 1334.2783012061132, "count": 232694, "is_parallel": true, "self": 40.88381932000925, "children": { "UnityEnvironment._generate_step_input": { "total": 86.68280187105864, "count": 232694, "is_parallel": true, "self": 86.68280187105864 }, "communicator.exchange": { "total": 1105.0603561879907, "count": 232694, "is_parallel": true, "self": 1105.0603561879907 }, "steps_from_proto": { "total": 101.65132382705457, "count": 232694, "is_parallel": true, "self": 38.33112964410316, "children": { "_process_rank_one_or_two_observation": { "total": 63.32019418295141, "count": 465388, "is_parallel": true, "self": 63.32019418295141 } } } } } } } } } } }, "trainer_advance": { "total": 553.0186843030547, "count": 232695, "self": 6.877545069999769, "children": { "process_trajectory": { "total": 144.99250170705346, "count": 232695, "self": 143.64793679905273, "children": { "RLTrainer._checkpoint": { "total": 1.3445649080007342, "count": 10, "self": 1.3445649080007342 } } }, "_update_policy": { "total": 401.1486375260014, "count": 97, "self": 341.2915179229957, "children": { "TorchPPOOptimizer.update": { "total": 59.857119603005685, "count": 2910, "self": 59.857119603005685 } } } } } } }, "trainer_threads": { "total": 1.4199999895936344e-06, "count": 1, "self": 1.4199999895936344e-06 }, "TrainerController._save_models": { "total": 0.18448658600027557, "count": 1, "self": 0.0027023010002267256, "children": { "RLTrainer._checkpoint": { "total": 0.18178428500004884, "count": 1, "self": 0.18178428500004884 } } } } } } }