---
title: "UMRAO: A Chess Endgame Tutor"
authors:
  - "Dinesh Gadwal"
  - "Jim E. Greer"
  - "Gordon I. McCalla"
doi: ""
url: "https://ijcai.org/proceedings/1991/159"
pdf: "https://ijcai.org/proceedings/1991/0159.pdf"
venue: "Proceedings of the Twelfth International Joint Conference on Artificial Intelligence"
year: 1991
pages: "1081-1085"
track: "Principles of AI Applications"
keywords:
---

# UMRAO: A Chess Endgame Tutor

Dinesh Gadwal, Jim E. Greer, Gordon I. McCalla

*Proceedings of the Twelfth International Joint Conference on Artificial Intelligence*, pages 1081-1085.

## Abstract

Most research in computer chess has focussed on creating an excellent chess player, with relatively little concern given to modelling how humans play chess. The research reported in this paper is aimed at investigating knowledge-based chess in the context of building a prototype chess tutor, UMRAO, which helps students learn how to play bishop-pawn endgames. In tutoring it is essential to take a knowledge-based approach, since students must learn how to manipulate strategic concepts, not how to carry out minimax search. UMRAO uses an extension of Michie's advice language to represent expert and novice chess plans. For any given endgame the system is able to compile the plans into a strategy graph, which elaborates strategies (both well-formed and ill-formed) that students might use as they solve the endgame problem. Strategy graphs can be compiled "off-line" so that they can be used in real time tutoring. We show that the normally rigid "model tracing" tutoring paradigm can be used in a flexible way in this domain.