{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.155360460281372, "min": 1.155360460281372, "max": 1.4170268774032593, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 57737.984375, "min": 56760.9375, "max": 76102.84375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.7421052631579, "min": 85.18072289156626, "max": 416.85833333333335, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49443.0, "min": 48898.0, "max": 50237.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49631.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49631.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.419564962387085, "min": 0.1287817358970642, "max": 2.419564962387085, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1379.1519775390625, "min": 15.325026512145996, "max": 1394.5548095703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.77542090551895, "min": 2.0270018244490906, "max": 3.9417839295450476, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2151.9899161458015, "min": 241.21321710944176, "max": 2240.0541476607323, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.77542090551895, "min": 2.0270018244490906, "max": 3.9417839295450476, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2151.9899161458015, "min": 241.21321710944176, "max": 2240.0541476607323, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.06742933498710606, "min": 0.06638521359917955, "max": 0.07542959116440215, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.13485866997421211, "min": 0.1327704271983591, "max": 0.2157607432206502, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04218596139883933, "min": 0.013628062972566113, "max": 0.04218596139883933, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08437192279767866, "min": 0.027256125945132225, "max": 0.11252502404580203, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.593623468824987e-06, "min": 4.593623468824987e-06, "max": 0.00029533845155385, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.187246937649973e-06, "min": 9.187246937649973e-06, "max": 0.0008440638186454, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101531175, "min": 0.101531175, "max": 0.19844615, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20306235, "min": 0.20306235, "max": 0.5813546, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.64056324999998e-05, "min": 8.64056324999998e-05, "max": 0.004922462884999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001728112649999996, "min": 0.0001728112649999996, "max": 0.014069594539999997, "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": "1677338458", "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": "1677341068" }, "total": 2610.211858171, "count": 1, "self": 0.3970047599996178, "children": { "run_training.setup": { "total": 0.11018421099993247, "count": 1, "self": 0.11018421099993247 }, "TrainerController.start_learning": { "total": 2609.7046692000004, "count": 1, "self": 3.9764165088804475, "children": { "TrainerController._reset_env": { "total": 10.470653653, "count": 1, "self": 10.470653653 }, "TrainerController.advance": { "total": 2595.14965524712, "count": 231383, "self": 4.490255687065655, "children": { "env_step": { "total": 1772.7544551780393, "count": 231383, "self": 1486.0676383619773, "children": { "SubprocessEnvManager._take_step": { "total": 284.08601014701753, "count": 231383, "self": 15.444536068925345, "children": { "TorchPolicy.evaluate": { "total": 268.6414740780922, "count": 222907, "self": 67.29148799511154, "children": { "TorchPolicy.sample_actions": { "total": 201.34998608298065, "count": 222907, "self": 201.34998608298065 } } } } }, "workers": { "total": 2.6008066690444593, "count": 231383, "self": 0.0, "children": { "worker_root": { "total": 2601.4805156938746, "count": 231383, "is_parallel": true, "self": 1396.5920414289194, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008852260000367096, "count": 1, "is_parallel": true, "self": 0.00030718500011062133, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005780409999260883, "count": 2, "is_parallel": true, "self": 0.0005780409999260883 } } }, "UnityEnvironment.step": { "total": 0.029832400000032067, "count": 1, "is_parallel": true, "self": 0.00031281100041269383, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003714979998221679, "count": 1, "is_parallel": true, "self": 0.0003714979998221679 }, "communicator.exchange": { "total": 0.02848267199988186, "count": 1, "is_parallel": true, "self": 0.02848267199988186 }, "steps_from_proto": { "total": 0.0006654189999153459, "count": 1, "is_parallel": true, "self": 0.00021971299975120928, "children": { "_process_rank_one_or_two_observation": { "total": 0.00044570600016413664, "count": 2, "is_parallel": true, "self": 0.00044570600016413664 } } } } } } }, "UnityEnvironment.step": { "total": 1204.8884742649552, "count": 231382, "is_parallel": true, "self": 37.57263266155792, "children": { "UnityEnvironment._generate_step_input": { "total": 78.01672643718689, "count": 231382, "is_parallel": true, "self": 78.01672643718689 }, "communicator.exchange": { "total": 999.9373294560505, "count": 231382, "is_parallel": true, "self": 999.9373294560505 }, "steps_from_proto": { "total": 89.3617857101599, "count": 231382, "is_parallel": true, "self": 36.289736526970955, "children": { "_process_rank_one_or_two_observation": { "total": 53.07204918318894, "count": 462764, "is_parallel": true, "self": 53.07204918318894 } } } } } } } } } } }, "trainer_advance": { "total": 817.9049443820147, "count": 231383, "self": 6.412810027999058, "children": { "process_trajectory": { "total": 158.56997422301652, "count": 231383, "self": 157.41246759901696, "children": { "RLTrainer._checkpoint": { "total": 1.1575066239995522, "count": 10, "self": 1.1575066239995522 } } }, "_update_policy": { "total": 652.9221601309991, "count": 96, "self": 317.9563261770247, "children": { "TorchPPOOptimizer.update": { "total": 334.9658339539744, "count": 46287, "self": 334.9658339539744 } } } } } } }, "trainer_threads": { "total": 8.189999789465219e-07, "count": 1, "self": 8.189999789465219e-07 }, "TrainerController._save_models": { "total": 0.10794297199981884, "count": 1, "self": 0.0021557760001087445, "children": { "RLTrainer._checkpoint": { "total": 0.10578719599971009, "count": 1, "self": 0.10578719599971009 } } } } } } }