GENERAL GAME‐PLAYING AND REINFORCEMENT LEARNING
作者:
Robert Levinson,
期刊:
Computational Intelligence
(WILEY Available online 1996)
卷期:
Volume 12,
issue 1
页码: 155-176
ISSN:0824-7935
年代: 1996
DOI:10.1111/j.1467-8640.1996.tb00257.x
出版商: Blackwell Publishing Ltd
关键词: games;mathematical structure;heuristic search;machine learning;hypergraphs;neural networks;analogical reasoning;RETE;relational patterns;hierarchical reinforcement learning
数据来源: WILEY
摘要:
This paper provides a blueprint for the development of a fully domain‐independent single‐agent and multiagent heuristic search system. It gives a graph‐theoretic representation of search problems based on conceptual graphs and outlines two different learning systems. One, an “informed learner”, makes use of the graph‐theoretic definition of a search problem or game in playing and adapting to a game in the given environment. The other, a “blind learner”, is not given access to the rules of a domain but must discover and then exploit the underlying mathematical structure of a given domain. Relevant work of others is referenced within the context of the blueprint.To illustrate further how one might go about creating general game‐playing agents, we show how we can generalize the understanding obtained with the Morph chess system to all games involving the interactions of abstract mathematical relations. A monitor for such domains has been developed, along with an implementation of a blind and informed learning system known as Morphll. Performance results with MorphK are preliminary but encouraging and provide a few more data points with which to understand and evalu
点击下载:
PDF
(1513KB)
返 回