{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4059581756591797, "min": 1.4059581756591797, "max": 1.429925799369812, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70948.8671875, "min": 69034.359375, "max": 78702.671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.77756286266924, "min": 82.36833333333334, "max": 425.3728813559322, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49517.0, "min": 48782.0, "max": 50194.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999878.0, "min": 49562.0, "max": 1999878.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999878.0, "min": 49562.0, "max": 1999878.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3990585803985596, "min": 0.03942776843905449, "max": 2.448760509490967, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1240.313232421875, "min": 4.613049030303955, "max": 1411.472900390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.707762011937523, "min": 1.8087251433449933, "max": 3.9526387194828754, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1916.9129601716995, "min": 211.6208417713642, "max": 2237.6122221946716, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.707762011937523, "min": 1.8087251433449933, "max": 3.9526387194828754, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1916.9129601716995, "min": 211.6208417713642, "max": 2237.6122221946716, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015816074667317378, "min": 0.013264522007021799, "max": 0.019630957622818336, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04744822400195214, "min": 0.02717152930078252, "max": 0.05401776190265081, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049597427331739, "min": 0.02211359894524018, "max": 0.05900045016573535, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.148792281995217, "min": 0.04422719789048036, "max": 0.17700135049720606, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3492488836166663e-06, "min": 3.3492488836166663e-06, "max": 0.00029533222655592494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.004774665085e-05, "min": 1.004774665085e-05, "max": 0.0008439733686755498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111638333333335, "min": 0.10111638333333335, "max": 0.198444075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30334915000000007, "min": 0.2073589, "max": 0.5813244499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.570752833333335e-05, "min": 6.570752833333335e-05, "max": 0.0049223593425, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019712258500000006, "min": 0.00019712258500000006, "max": 0.014068090055000001, "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": "1671415934", "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": "1671418208" }, "total": 2273.8032198210003, "count": 1, "self": 0.44038679699997374, "children": { "run_training.setup": { "total": 0.10569204199998694, "count": 1, "self": 0.10569204199998694 }, "TrainerController.start_learning": { "total": 2273.2571409820002, "count": 1, "self": 3.984188135128079, "children": { "TrainerController._reset_env": { "total": 7.997462727000027, "count": 1, "self": 7.997462727000027 }, "TrainerController.advance": { "total": 2261.145743432872, "count": 232143, "self": 4.051384617995154, "children": { "env_step": { "total": 1766.9859284739516, "count": 232143, "self": 1482.9029063130863, "children": { "SubprocessEnvManager._take_step": { "total": 281.4863710389388, "count": 232143, "self": 15.128319066883478, "children": { "TorchPolicy.evaluate": { "total": 266.3580519720553, "count": 222974, "self": 65.94156160505844, "children": { "TorchPolicy.sample_actions": { "total": 200.41649036699687, "count": 222974, "self": 200.41649036699687 } } } } }, "workers": { "total": 2.596651121926527, "count": 232143, "self": 0.0, "children": { "worker_root": { "total": 2265.4227216960026, "count": 232143, "is_parallel": true, "self": 1042.1595190480184, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002089289000025474, "count": 1, "is_parallel": true, "self": 0.0003303600000208462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017589290000046276, "count": 2, "is_parallel": true, "self": 0.0017589290000046276 } } }, "UnityEnvironment.step": { "total": 0.0267946410000377, "count": 1, "is_parallel": true, "self": 0.0002910030000293773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018439400002989714, "count": 1, "is_parallel": true, "self": 0.00018439400002989714 }, "communicator.exchange": { "total": 0.025534542000002602, "count": 1, "is_parallel": true, "self": 0.025534542000002602 }, "steps_from_proto": { "total": 0.0007847019999758231, "count": 1, "is_parallel": true, "self": 0.0002595639999753985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005251380000004247, "count": 2, "is_parallel": true, "self": 0.0005251380000004247 } } } } } } }, "UnityEnvironment.step": { "total": 1223.2632026479841, "count": 232142, "is_parallel": true, "self": 35.069320337108365, "children": { "UnityEnvironment._generate_step_input": { "total": 76.92821104305438, "count": 232142, "is_parallel": true, "self": 76.92821104305438 }, "communicator.exchange": { "total": 1017.2126069248886, "count": 232142, "is_parallel": true, "self": 1017.2126069248886 }, "steps_from_proto": { "total": 94.05306434293283, "count": 232142, "is_parallel": true, "self": 38.50863448489855, "children": { "_process_rank_one_or_two_observation": { "total": 55.54442985803428, "count": 464284, "is_parallel": true, "self": 55.54442985803428 } } } } } } } } } } }, "trainer_advance": { "total": 490.1084303409254, "count": 232143, "self": 5.997872446861038, "children": { "process_trajectory": { "total": 149.78752933906458, "count": 232143, "self": 148.53926891206413, "children": { "RLTrainer._checkpoint": { "total": 1.2482604270004458, "count": 10, "self": 1.2482604270004458 } } }, "_update_policy": { "total": 334.3230285549998, "count": 97, "self": 280.4201583250054, "children": { "TorchPPOOptimizer.update": { "total": 53.90287022999439, "count": 2910, "self": 53.90287022999439 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.12974574500003655, "count": 1, "self": 0.0020871170004284068, "children": { "RLTrainer._checkpoint": { "total": 0.12765862799960814, "count": 1, "self": 0.12765862799960814 } } } } } } }