16
IRUS Total
Downloads
  Altmetric

Machine discovery of comprehensible strategies for simple games using Meta-interpretive Learning

File Description SizeFormat 
Muggleton-Hocquette2019_Article_MachineDiscoveryOfComprehensib.pdfPublished version1.46 MBAdobe PDFView/Open
Title: Machine discovery of comprehensible strategies for simple games using Meta-interpretive Learning
Authors: Muggleton, SH
Hocquette, C
Item Type: Journal Article
Abstract: Recently, world-class human players have been outperformed in a number of complex two-person games (Go, Chess, Checkers) by Deep Reinforcement Learning systems. However, the data efficiency of the learning systems is unclear given that they appear to require far more training games to achieve such performance than any human player might experience in a lifetime. In addition, the resulting learned strategies are not in a form which can be communicated to human players. This contrasts to earlier research in Behavioural Cloning in which single-agent skills were machine learned in a symbolic language, facilitating their being taught to human beings. In this paper, we consider Machine Discovery of human-comprehensible strategies for simple two-person games (Noughts-and-Crosses and Hexapawn). One advantage of considering simple games is that there is a tractable approach to calculating minimax regret. We use these games to compare Cumulative Minimax Regret for variants of both standard and deep reinforcement learning against two variants of a new Meta-interpretive Learning system called MIGO. In our experiments, tested variants of both normal and deep reinforcement learning have consistently worse performance (higher cumulative minimax regret) than both variants of MIGO on Noughts-and-Crosses and Hexapawn. In addition, MIGO’s learned rules are relatively easy to comprehend, and are demonstrated to achieve significant transfer learning in both directions between Noughts-and-Crosses and Hexapawn.
Issue Date: 1-Apr-2019
Date of Acceptance: 19-Mar-2019
URI: http://hdl.handle.net/10044/1/72911
DOI: https://dx.doi.org/10.1007/s00354-019-00054-2
ISSN: 0288-3635
Publisher: Springer (part of Springer Nature)
Start Page: 203
End Page: 217
Journal / Book Title: New Generation Computing
Volume: 37
Issue: 2
Copyright Statement: © The Author(s) 2019. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Keywords: Science & Technology
Technology
Computer Science, Hardware & Architecture
Computer Science, Theory & Methods
Computer Science
Inductive Logic Programming
Reinforcement learning
Games strategies
Science & Technology
Technology
Computer Science, Hardware & Architecture
Computer Science, Theory & Methods
Computer Science
Inductive Logic Programming
Reinforcement learning
Games strategies
0801 Artificial Intelligence and Image Processing
0803 Computer Software
1702 Cognitive Sciences
Information Systems
Publication Status: Published
Online Publication Date: 2019-04-25
Appears in Collections:Computing