GENERAL GAME‐PLAYING AND REINFORCEMENT LEARNING
Abstract
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 evaluate the blueprint.
Number of times cited: 4
- Nathan Companez and Aldeida Aleti, Can Monte-Carlo Tree Search learn to sacrifice?, Journal of Heuristics, 22, 6, (783), (2016). 2014 9th Computing Colombian Conference (9CCC) Pereira, Colombia 2014 9th Computing Colombian Conference (9CCC) IEEE , (2014). 978-1-4799-6717-9 Leonardo Quinonez and Jonatan Gomez General videogame learning with neural-evolution , (2014). 207 212 6955333 , 10.1109/ColumbianCC.2014.6955333 http://ieeexplore.ieee.org/document/6955333/ 2010 4th IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO) Budapest, Hungary 2010 Fourth IEEE International Conference on Self-Adaptive and Self-Organizing Systems IEEE , (2010). 978-1-4244-8537-6 Nicolas Honing and Han La Poutre Designing Comprehensible Self-Organising Systems , (2010). 233 242 5630185 , 10.1109/SASO.2010.18 http://ieeexplore.ieee.org/document/5630185/
- John F Sowa, Semantic Networks, Encyclopedia of Cognitive Science, (2006).
