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!
Description
Summary: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.
ISSN:1424-8220