This paper presents Abalearn, a self-teaching Abalone program capable of automatically reaching an intermediate level of play without needing expert-labeled training examples, deep searches or exposure to competent play. Our approach is based on a reinforcement learning algorithm that is risk-seeking, since defensive players in Abalone tend to never end a game. We show that it is the risk-sensitivity that allows a successful self-play training. We also propose a set of features that seem relevant for achieving a good level of play. We evaluate our approach using a fixed heuristic opponent as a benchmark, pitting our agents against human players online and comparing samples of our agents at different times of training.
CITATION STYLE
Campos, P., & Langlois, T. (2003). Abalearn: A risk-sensitive approach to self-play learning in Abalone. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2837, pp. 35–46). Springer Verlag. https://doi.org/10.1007/978-3-540-39857-8_6
Mendeley helps you to discover research relevant for your work.