zbMATH — the first resource for mathematics

Argumentation-based reinforcement learning for RoboCup soccer Keepaway. (English) Zbl 1327.68191
De Raedt, Luc (ed.) et al., ECAI 2012. 20th European conference on artificial intelligence, Montpellier, France, August 27–31, 2012. Proceedings. Including proceedings of the 7th conference on prestigious applications of artificial intelligence (PAIS-2012) and the system demonstrations track. Amsterdam: IOS Press (ISBN 978-1-61499-097-0/pbk; 978-1-61499-098-7/ebook). Frontiers in Artificial Intelligence and Applications 242, 342-347 (2012).
Summary: Reinforcement Learning (RL) suffers from several difficulties when applied to domains with no obvious goal state defined; this leads to inefficiency in RL algorithms. In this paper we consider a solution within the context of a widely-used testbed for RL, that of RoboCup Keepaway soccer. We introduce Argumentation-Based RL (ABRL), using methods from argumentation theory to integrate domain knowledge, represented by arguments, into the SMDP algorithm for RL by using potential-based reward shaping. Empirical results show that ABRL outperforms the original SMDP algorithm, for this game, by improving the optimal performance.
For the entire collection see [Zbl 1272.68015].

68T05 Learning and adaptive systems in artificial intelligence
68T40 Artificial intelligence for robotics
Full Text: Link