Transfer learning in real-time strategy games using hybrid CBR/RL

Abstract

The goal of transfer learning is to use the knowl-edge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multi-layered architecture named CAse-Based Reinforce-ment Learner (CARL). It uses a novel combina-tion of Case-Based Reasoning (CBR) and Rein-forcement Learning (RL) to achieve transfer while playing against the Game AI across a variety of scenarios in MadRTSTM, a commercial Real Time Strategy game. Our experiments demonstrate that CARL not only performs well on individual tasks but also exhibits significant performance gains when allowed to transfer knowledge from previous