Representation Learning for Context-Dependent Decision-Making

Humans are capable of adjusting to changing environments flexibly and quickly. Empirical evidence has revealed that representation learning plays a crucial role in endowing humans with such a capability. Inspired by this observation, we study representation learning in the sequential decision-making...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Qin, Yuzhen, Menara, Tommaso, Samet Oymak, ShiNung Ching, Pasqualetti, Fabio
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.05.2022
Subjects
Algorithms
Changing environments
Context
Decision making
Machine learning
Representations
Sorting algorithms
Online AccessGet full text

Cover

More Information
Summary:Humans are capable of adjusting to changing environments flexibly and quickly. Empirical evidence has revealed that representation learning plays a crucial role in endowing humans with such a capability. Inspired by this observation, we study representation learning in the sequential decision-making scenario with contextual changes. We propose an online algorithm that is able to learn and transfer context-dependent representations and show that it significantly outperforms the existing ones that do not learn representations adaptively. As a case study, we apply our algorithm to the Wisconsin Card Sorting Task, a well-established test for the mental flexibility of humans in sequential decision-making. By comparing our algorithm with the standard Q-learning and Deep-Q learning algorithms, we demonstrate the benefits of adaptive representation learning.
ISSN:2331-8422