{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4045161008834839, "min": 1.4045110940933228, "max": 1.4275330305099487, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70277.7734375, "min": 67935.3125, "max": 75234.3359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.38910505836576, "min": 84.20102214650767, "max": 390.8046875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49544.0, "min": 48860.0, "max": 50094.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999944.0, "min": 49581.0, "max": 1999944.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999944.0, "min": 49581.0, "max": 1999944.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4489691257476807, "min": 0.02115306816995144, "max": 2.4624955654144287, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1258.7701416015625, "min": 2.6864397525787354, "max": 1410.11962890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8937121655226683, "min": 1.8972659012464088, "max": 3.960493353369472, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2001.3680530786514, "min": 240.95276945829391, "max": 2240.684354186058, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8937121655226683, "min": 1.8972659012464088, "max": 3.960493353369472, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2001.3680530786514, "min": 240.95276945829391, "max": 2240.684354186058, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018453275749602146, "min": 0.01366751354119818, "max": 0.019830748764151293, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05535982724880644, "min": 0.02733502708239636, "max": 0.05949224629245388, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05277219981782966, "min": 0.02496958722670873, "max": 0.058941075267891094, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15831659945348897, "min": 0.04993917445341746, "max": 0.17559698621431988, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.365548878183337e-06, "min": 3.365548878183337e-06, "max": 0.000295344376551875, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0096646634550011e-05, "min": 1.0096646634550011e-05, "max": 0.0008440327686557499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112181666666668, "min": 0.10112181666666668, "max": 0.19844812500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30336545000000004, "min": 0.20740935, "max": 0.58134425, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.597865166666671e-05, "min": 6.597865166666671e-05, "max": 0.0049225614375, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019793595500000014, "min": 0.00019793595500000014, "max": 0.014069078074999998, "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": "1678284459", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678286797" }, "total": 2337.708342186, "count": 1, "self": 0.8096058639998773, "children": { "run_training.setup": { "total": 0.18311401599999044, "count": 1, "self": 0.18311401599999044 }, "TrainerController.start_learning": { "total": 2336.715622306, "count": 1, "self": 3.868485747066188, "children": { "TrainerController._reset_env": { "total": 10.020093912999982, "count": 1, "self": 10.020093912999982 }, "TrainerController.advance": { "total": 2322.6403090369336, "count": 231882, "self": 4.251054592949458, "children": { "env_step": { "total": 1813.4026920779866, "count": 231882, "self": 1514.1082857669026, "children": { "SubprocessEnvManager._take_step": { "total": 296.6156417959802, "count": 231882, "self": 15.531500644874768, "children": { "TorchPolicy.evaluate": { "total": 281.0841411511054, "count": 222984, "self": 70.52141462514987, "children": { "TorchPolicy.sample_actions": { "total": 210.56272652595555, "count": 222984, "self": 210.56272652595555 } } } } }, "workers": { "total": 2.6787645151039214, "count": 231882, "self": 0.0, "children": { "worker_root": { "total": 2328.556424901, "count": 231882, "is_parallel": true, "self": 1095.9175848310583, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010584480000943586, "count": 1, "is_parallel": true, "self": 0.0003930760001367162, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006653719999576424, "count": 2, "is_parallel": true, "self": 0.0006653719999576424 } } }, "UnityEnvironment.step": { "total": 0.032442165000020395, "count": 1, "is_parallel": true, "self": 0.00032726000017646584, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002041189999317794, "count": 1, "is_parallel": true, "self": 0.0002041189999317794 }, "communicator.exchange": { "total": 0.028009286999918004, "count": 1, "is_parallel": true, "self": 0.028009286999918004 }, "steps_from_proto": { "total": 0.0039014989999941463, "count": 1, "is_parallel": true, "self": 0.0002778820000912674, "children": { "_process_rank_one_or_two_observation": { "total": 0.003623616999902879, "count": 2, "is_parallel": true, "self": 0.003623616999902879 } } } } } } }, "UnityEnvironment.step": { "total": 1232.6388400699416, "count": 231881, "is_parallel": true, "self": 37.73534189999009, "children": { "UnityEnvironment._generate_step_input": { "total": 77.00453629897015, "count": 231881, "is_parallel": true, "self": 77.00453629897015 }, "communicator.exchange": { "total": 1026.9068216520418, "count": 231881, "is_parallel": true, "self": 1026.9068216520418 }, "steps_from_proto": { "total": 90.99214021893943, "count": 231881, "is_parallel": true, "self": 36.665840733058644, "children": { "_process_rank_one_or_two_observation": { "total": 54.32629948588078, "count": 463762, "is_parallel": true, "self": 54.32629948588078 } } } } } } } } } } }, "trainer_advance": { "total": 504.98656236599754, "count": 231882, "self": 6.100954242939565, "children": { "process_trajectory": { "total": 159.3410060220599, "count": 231882, "self": 157.8918619670594, "children": { "RLTrainer._checkpoint": { "total": 1.4491440550004882, "count": 10, "self": 1.4491440550004882 } } }, "_update_policy": { "total": 339.5446021009981, "count": 97, "self": 282.95650638898724, "children": { "TorchPPOOptimizer.update": { "total": 56.58809571201084, "count": 2910, "self": 56.58809571201084 } } } } } } }, "trainer_threads": { "total": 1.2059999789926223e-06, "count": 1, "self": 1.2059999789926223e-06 }, "TrainerController._save_models": { "total": 0.1867324030004056, "count": 1, "self": 0.002873195000574924, "children": { "RLTrainer._checkpoint": { "total": 0.1838592079998307, "count": 1, "self": 0.1838592079998307 } } } } } } }