{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4110133647918701, "min": 1.4110133647918701, "max": 1.428300142288208, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71208.203125, "min": 68479.5546875, "max": 77896.265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.72393822393822, "min": 85.23316062176166, "max": 405.85483870967744, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49585.0, "min": 48893.0, "max": 50326.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999753.0, "min": 49777.0, "max": 1999753.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999753.0, "min": 49777.0, "max": 1999753.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4523825645446777, "min": 0.050116196274757385, "max": 2.460679531097412, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1270.334228515625, "min": 6.164292335510254, "max": 1382.3427734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.693256701281632, "min": 1.7910528242345747, "max": 4.007259015550892, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1913.1069712638855, "min": 220.2994973808527, "max": 2238.349613249302, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.693256701281632, "min": 1.7910528242345747, "max": 4.007259015550892, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1913.1069712638855, "min": 220.2994973808527, "max": 2238.349613249302, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015624674615941733, "min": 0.013962732798083582, "max": 0.021263179999368734, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0468740238478252, "min": 0.028827495485772184, "max": 0.055318719231096714, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05443692832357353, "min": 0.0221285467967391, "max": 0.061107353824708194, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1633107849707206, "min": 0.0442570935934782, "max": 0.18332206147412458, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3833988722333345e-06, "min": 3.3833988722333345e-06, "max": 0.0002953364265545249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0150196616700004e-05, "min": 1.0150196616700004e-05, "max": 0.0008439487686837499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112776666666667, "min": 0.10112776666666667, "max": 0.19844547500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033833, "min": 0.20743215000000004, "max": 0.5813162500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.627555666666666e-05, "min": 6.627555666666666e-05, "max": 0.0049224292025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019882667, "min": 0.00019882667, "max": 0.014067680874999999, "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": "1678067189", "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": "1678069569" }, "total": 2379.708924032, "count": 1, "self": 0.7424152529997627, "children": { "run_training.setup": { "total": 0.17765176199998223, "count": 1, "self": 0.17765176199998223 }, "TrainerController.start_learning": { "total": 2378.7888570170003, "count": 1, "self": 4.162354855911417, "children": { "TrainerController._reset_env": { "total": 10.158303074999935, "count": 1, "self": 10.158303074999935 }, "TrainerController.advance": { "total": 2364.286839093089, "count": 232098, "self": 4.329445956066593, "children": { "env_step": { "total": 1835.565468177018, "count": 232098, "self": 1533.6259325429355, "children": { "SubprocessEnvManager._take_step": { "total": 299.1211903480487, "count": 232098, "self": 15.87003025013405, "children": { "TorchPolicy.evaluate": { "total": 283.25116009791464, "count": 223023, "self": 70.71567520483586, "children": { "TorchPolicy.sample_actions": { "total": 212.53548489307877, "count": 223023, "self": 212.53548489307877 } } } } }, "workers": { "total": 2.818345286033832, "count": 232098, "self": 0.0, "children": { "worker_root": { "total": 2370.1519032069173, "count": 232098, "is_parallel": true, "self": 1126.3375634739991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010470650000797832, "count": 1, "is_parallel": true, "self": 0.00038066000001890643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006664050000608768, "count": 2, "is_parallel": true, "self": 0.0006664050000608768 } } }, "UnityEnvironment.step": { "total": 0.02788609699996414, "count": 1, "is_parallel": true, "self": 0.00029806499992446334, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000205161000053522, "count": 1, "is_parallel": true, "self": 0.000205161000053522 }, "communicator.exchange": { "total": 0.026648138999917137, "count": 1, "is_parallel": true, "self": 0.026648138999917137 }, "steps_from_proto": { "total": 0.0007347320000690161, "count": 1, "is_parallel": true, "self": 0.00023427899998296198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005004530000860541, "count": 2, "is_parallel": true, "self": 0.0005004530000860541 } } } } } } }, "UnityEnvironment.step": { "total": 1243.8143397329181, "count": 232097, "is_parallel": true, "self": 38.25906511914445, "children": { "UnityEnvironment._generate_step_input": { "total": 77.97812403689625, "count": 232097, "is_parallel": true, "self": 77.97812403689625 }, "communicator.exchange": { "total": 1036.8741973019016, "count": 232097, "is_parallel": true, "self": 1036.8741973019016 }, "steps_from_proto": { "total": 90.7029532749757, "count": 232097, "is_parallel": true, "self": 36.06485789285364, "children": { "_process_rank_one_or_two_observation": { "total": 54.63809538212206, "count": 464194, "is_parallel": true, "self": 54.63809538212206 } } } } } } } } } } }, "trainer_advance": { "total": 524.3919249600042, "count": 232098, "self": 6.608345096936546, "children": { "process_trajectory": { "total": 163.2918888240673, "count": 232098, "self": 161.83677214306704, "children": { "RLTrainer._checkpoint": { "total": 1.455116681000277, "count": 10, "self": 1.455116681000277 } } }, "_update_policy": { "total": 354.49169103900033, "count": 97, "self": 296.5192060040059, "children": { "TorchPPOOptimizer.update": { "total": 57.972485034994406, "count": 2910, "self": 57.972485034994406 } } } } } } }, "trainer_threads": { "total": 1.1729998732334934e-06, "count": 1, "self": 1.1729998732334934e-06 }, "TrainerController._save_models": { "total": 0.1813588200002414, "count": 1, "self": 0.0028661530000135826, "children": { "RLTrainer._checkpoint": { "total": 0.1784926670002278, "count": 1, "self": 0.1784926670002278 } } } } } } }