Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze

In this study, we investigate the adaptability of artificial agents within a noisy T-maze that use Markov decision processes (MDPs) and successor feature (SF) and predecessor feature (PF) learning algorithms. Our focus is on quantifying how varying the hyperparameters, specifically the reward learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Incheol Seo, Hyunsu Lee
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/19/6419
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850284200598437888
author Incheol Seo
Hyunsu Lee
author_facet Incheol Seo
Hyunsu Lee
author_sort Incheol Seo
collection DOAJ
description In this study, we investigate the adaptability of artificial agents within a noisy T-maze that use Markov decision processes (MDPs) and successor feature (SF) and predecessor feature (PF) learning algorithms. Our focus is on quantifying how varying the hyperparameters, specifically the reward learning rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>α</mi><mi>r</mi></msub></semantics></math></inline-formula>) and the eligibility trace decay rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula>), can enhance their adaptability. Adaptation is evaluated by analyzing the hyperparameters of cumulative reward, step length, adaptation rate, and adaptation step length and the relationships between them using Spearman’s correlation tests and linear regression. Our findings reveal that an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>α</mi><mi>r</mi></msub></semantics></math></inline-formula> of 0.9 consistently yields superior adaptation across all metrics at a noise level of 0.05. However, the optimal setting for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> varies by metric and context. In discussing these results, we emphasize the critical role of hyperparameter optimization in refining the performance and transfer learning efficacy of learning algorithms. This research advances our understanding of the functionality of PF and SF algorithms, particularly in navigating the inherent uncertainty of transfer learning tasks. By offering insights into the optimal hyperparameter configurations, this study contributes to the development of more adaptive and robust learning algorithms, paving the way for future explorations in artificial intelligence and neuroscience.
format Article
id doaj-art-77473eb5bfab470fa6f5648faf36aac1
institution OA Journals
issn 1424-8220
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-77473eb5bfab470fa6f5648faf36aac12025-08-20T01:47:37ZengMDPI AGSensors1424-82202024-10-012419641910.3390/s24196419Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-MazeIncheol Seo0Hyunsu Lee1Department of Immunology, Kyungpook National University School of Medicine, Daegu 41944, Republic of KoreaDepartment of Physiology, Pusan National University School of Medicine, Yangsan 50612, Republic of KoreaIn this study, we investigate the adaptability of artificial agents within a noisy T-maze that use Markov decision processes (MDPs) and successor feature (SF) and predecessor feature (PF) learning algorithms. Our focus is on quantifying how varying the hyperparameters, specifically the reward learning rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>α</mi><mi>r</mi></msub></semantics></math></inline-formula>) and the eligibility trace decay rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula>), can enhance their adaptability. Adaptation is evaluated by analyzing the hyperparameters of cumulative reward, step length, adaptation rate, and adaptation step length and the relationships between them using Spearman’s correlation tests and linear regression. Our findings reveal that an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>α</mi><mi>r</mi></msub></semantics></math></inline-formula> of 0.9 consistently yields superior adaptation across all metrics at a noise level of 0.05. However, the optimal setting for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> varies by metric and context. In discussing these results, we emphasize the critical role of hyperparameter optimization in refining the performance and transfer learning efficacy of learning algorithms. This research advances our understanding of the functionality of PF and SF algorithms, particularly in navigating the inherent uncertainty of transfer learning tasks. By offering insights into the optimal hyperparameter configurations, this study contributes to the development of more adaptive and robust learning algorithms, paving the way for future explorations in artificial intelligence and neuroscience.https://www.mdpi.com/1424-8220/24/19/6419reinforcement learningT-maze transfer learninghyperparameter tuningrobustnesspredecessor featuresnoisy observation
spellingShingle Incheol Seo
Hyunsu Lee
Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze
Sensors
reinforcement learning
T-maze transfer learning
hyperparameter tuning
robustness
predecessor features
noisy observation
title Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze
title_full Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze
title_fullStr Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze
title_full_unstemmed Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze
title_short Investigating Transfer Learning in Noisy Environments: A Study of Predecessor and Successor Features in Spatial Learning Using a T-Maze
title_sort investigating transfer learning in noisy environments a study of predecessor and successor features in spatial learning using a t maze
topic reinforcement learning
T-maze transfer learning
hyperparameter tuning
robustness
predecessor features
noisy observation
url https://www.mdpi.com/1424-8220/24/19/6419
work_keys_str_mv AT incheolseo investigatingtransferlearninginnoisyenvironmentsastudyofpredecessorandsuccessorfeaturesinspatiallearningusingatmaze
AT hyunsulee investigatingtransferlearninginnoisyenvironmentsastudyofpredecessorandsuccessorfeaturesinspatiallearningusingatmaze