Learning the Rules of the Game: An Interpretable AI for Learning How To Play

In this paper we present an interpretable artificial intelligence, and its associated machine learning algorithm, that is capable of automatically learning the rules of a game whenever the rules the relationship between a player's current state and their corresponding set of legal moves can be...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on games 2022-06, Vol.14 (2), p.1-1
Main Authors: Aurentz, Jared, Martinez Navarro, Adrian, Rios Insua, David
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Boolean algebra
Boolean functions
Card games
game rules
Games
interpretable artificial intelligence
Law
Machine learning
Machine learning algorithms
Neural networks
Polynomials
Representations
Tiles
Training
Zhegalkin polynomials
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we present an interpretable artificial intelligence, and its associated machine learning algorithm, that is capable of automatically learning the rules of a game whenever the rules the relationship between a player's current state and their corresponding set of legal moves can be represented as a set of low degree Zhegalkin polynomials, a special class of Boolean functions. This is true for many popular games including Spanish Domin and the card game President. Our method takes advantage of the low polynomial degree to compute an exact representation of the rules in polynomial time instead of the required exponential time for generic Boolean functions. The rules can also be represented using significantly less storage than in the generic case which, for many games, leads to a representation that is easy to interpret.
ISSN:2475-1502
2475-1510
DOI:10.1109/TG.2021.3066245