Abstract
This review looks at some of the central relationships between artificial intelligence, psychology, and economics through the lens of information theory, specifically focusing on formal models of decision-theory. In doing so we look at a particular approach that each field has adopted and how information theory has informed the development of the ideas of each field. A key theme is expected utility theory, its connection to information theory, the Bayesian approach to decision-making and forms of (bounded) rationality. What emerges from this review is a broadly unified formal perspective derived from three very different starting points that reflect the unique principles of each field. Each of the three approaches reviewed can, in principle at least, be implemented in a computational model in such a way that, with sufficient computational power, they could be compared with human abilities in complex tasks. However, a central critique that can be applied to all three approaches was first put forward by Savage in The Foundations of Statistics and recently brought to the fore by the economist Binmore: Bayesian approaches to decision-making work in what Savage called ‘small worlds’ but cannot work in ‘large worlds’. This point, in various different guises, is central to some of the current debates about the power of artificial intelligence and its relationship to human-like learning and decision-making. Recent work on artificial intelligence has gone some way to bridging this gap but significant questions remain to be answered in all three fields in order to make progress in producing realistic models of human decision-making in the real world in which we live in.
Highlights
Accepted: 4 March 2021The goal of this article is to review a relatively unexplored but interesting intersection between three different research areas that motivated the special issue this article appears in: economics, artificial intelligence, and psychology
In this Introduction we very briefly cover some earlier uses of information theory in each field, and more details are given before describing how the article is structured
This axiomatic approach has played a fundamental role in expected utility theory, but important is the subsequent relationship between utility and rationality that informs the interpretation of economic rationality in the context of psychological or cognitive processes
Summary
The goal of this article is to review a relatively unexplored but interesting intersection between three different research areas that motivated the special issue this article appears in: economics, artificial intelligence, and psychology. On the other hand there is an extensive body of work that uses AI as a tool for the analysis of large and complex data-sets and these are less concerned with what this tells us about human cognition and decision-making These methods often make use of ideas from information theory in order to improve performance, for example in feature selection tasks mutual information is used to measure the relevance of different features [39]. As well as feature selection using entropy-based filters [40], information gain methods [41], one-shot learning [42], and deep learning [43] In these applications information theory plays an important role, but the emphasis is towards the practical implementation of effective algorithms for data analysis, rather than the foundations of decision-making. There are many other ways to have sliced and diced these topics, but I hope the mix that appears here provides an interesting and illuminating perspective
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
