Argumentation-Based Reinforcement Learning for RoboCup Soccer Keepaway

摘要

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.