{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050477743148804, "min": 1.4050477743148804, "max": 1.4266163110733032, "count": 28 }, "Huggy.Policy.Entropy.sum": { "value": 68965.3671875, "min": 68373.0, "max": 78128.8359375, "count": 28 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.61048689138576, "min": 92.26070763500931, "max": 381.63358778625957, "count": 28 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49454.0, "min": 48896.0, "max": 50286.0, "count": 28 }, "Huggy.Step.mean": { "value": 1399862.0, "min": 49661.0, "max": 1399862.0, "count": 28 }, "Huggy.Step.sum": { "value": 1399862.0, "min": 49661.0, "max": 1399862.0, "count": 28 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.412247896194458, "min": 0.04033297672867775, "max": 2.412247896194458, "count": 28 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1288.140380859375, "min": 5.243287086486816, "max": 1288.140380859375, "count": 28 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.843937123982647, "min": 1.7883344732798063, "max": 3.843937123982647, "count": 28 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2052.6624242067337, "min": 232.48348152637482, "max": 2052.6624242067337, "count": 28 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.843937123982647, "min": 1.7883344732798063, "max": 3.843937123982647, "count": 28 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2052.6624242067337, "min": 232.48348152637482, "max": 2052.6624242067337, "count": 28 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017574884952045976, "min": 0.014049071767264346, "max": 0.021189645522463253, "count": 28 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03514976990409195, "min": 0.02809814353452869, "max": 0.05754970134366885, "count": 28 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04835774625341098, "min": 0.023676962653795878, "max": 0.06638217829167843, "count": 28 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09671549250682196, "min": 0.047353925307591756, "max": 0.17775745404263338, "count": 28 }, "Huggy.Policy.LearningRate.mean": { "value": 9.443856852050001e-05, "min": 9.443856852050001e-05, "max": 0.00029532285155904993, "count": 28 }, "Huggy.Policy.LearningRate.sum": { "value": 0.00018887713704100002, "min": 0.00018887713704100002, "max": 0.0008439072186975998, "count": 28 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1314795, "min": 0.1314795, "max": 0.19844095000000006, "count": 28 }, "Huggy.Policy.Epsilon.sum": { "value": 0.262959, "min": 0.262959, "max": 0.5813023999999999, "count": 28 }, "Huggy.Policy.Beta.mean": { "value": 0.0015808270500000004, "min": 0.0015808270500000004, "max": 0.004922203404999999, "count": 28 }, "Huggy.Policy.Beta.sum": { "value": 0.0031616541000000008, "min": 0.0031616541000000008, "max": 0.014066989760000002, "count": 28 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 28 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 28 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695781872", "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": "1695785360" }, "total": 3488.479489008, "count": 1, "self": 0.19305763100010154, "children": { "run_training.setup": { "total": 0.0833774379998431, "count": 1, "self": 0.0833774379998431 }, "TrainerController.start_learning": { "total": 3488.2030539390003, "count": 1, "self": 6.874610159091844, "children": { "TrainerController._reset_env": { "total": 3.6452988999999434, "count": 1, "self": 3.6452988999999434 }, "TrainerController.advance": { "total": 3477.4720118649093, "count": 164385, "self": 6.252857153788227, "children": { "env_step": { "total": 2188.9176167390433, "count": 164385, "self": 1845.5092080951572, "children": { "SubprocessEnvManager._take_step": { "total": 339.1871227439274, "count": 164385, "self": 22.379092333979543, "children": { "TorchPolicy.evaluate": { "total": 316.80803040994783, "count": 158511, "self": 316.80803040994783 } } }, "workers": { "total": 4.22128589995873, "count": 164385, "self": 0.0, "children": { "worker_root": { "total": 3473.659626063987, "count": 164385, "is_parallel": true, "self": 1995.3563525058669, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001837806000139608, "count": 1, "is_parallel": true, "self": 0.0005831600001329207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012546460000066872, "count": 2, "is_parallel": true, "self": 0.0012546460000066872 } } }, "UnityEnvironment.step": { "total": 0.05244202099993345, "count": 1, "is_parallel": true, "self": 0.0004580399997848872, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027220900005886506, "count": 1, "is_parallel": true, "self": 0.00027220900005886506 }, "communicator.exchange": { "total": 0.050569131999964156, "count": 1, "is_parallel": true, "self": 0.050569131999964156 }, "steps_from_proto": { "total": 0.0011426400001255388, "count": 1, "is_parallel": true, "self": 0.00026607700010572444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008765630000198144, "count": 2, "is_parallel": true, "self": 0.0008765630000198144 } } } } } } }, "UnityEnvironment.step": { "total": 1478.3032735581203, "count": 164384, "is_parallel": true, "self": 45.62271836716536, "children": { "UnityEnvironment._generate_step_input": { "total": 65.79932106096999, "count": 164384, "is_parallel": true, "self": 65.79932106096999 }, "communicator.exchange": { "total": 1260.8888446529384, "count": 164384, "is_parallel": true, "self": 1260.8888446529384 }, "steps_from_proto": { "total": 105.99238947704657, "count": 164384, "is_parallel": true, "self": 34.78361938103876, "children": { "_process_rank_one_or_two_observation": { "total": 71.20877009600781, "count": 328768, "is_parallel": true, "self": 71.20877009600781 } } } } } } } } } } }, "trainer_advance": { "total": 1282.3015379720778, "count": 164385, "self": 9.472835424177902, "children": { "process_trajectory": { "total": 172.62445528389617, "count": 164385, "self": 171.39473879189586, "children": { "RLTrainer._checkpoint": { "total": 1.229716492000307, "count": 7, "self": 1.229716492000307 } } }, "_update_policy": { "total": 1100.2042472640037, "count": 69, "self": 327.76083853499927, "children": { "TorchPPOOptimizer.update": { "total": 772.4434087290044, "count": 2048, "self": 772.4434087290044 } } } } } } }, "trainer_threads": { "total": 2.1879995983908884e-06, "count": 1, "self": 2.1879995983908884e-06 }, "TrainerController._save_models": { "total": 0.21113082699957886, "count": 1, "self": 0.007646924999789917, "children": { "RLTrainer._checkpoint": { "total": 0.20348390199978894, "count": 1, "self": 0.20348390199978894 } } } } } } }