06069365

a

06069365 Boutsioukis, Georgios Partalas, Ioannis Vlahavas, Ioannis Transfer learning in multi-agent reinforcement learning domains. Sanner, Scott (ed.) et al., Recent advances in reinforcement learning. 9th European workshop, EWRL 2011, Athens, Greece, September 9--11, 2011. Revised selected papers. Berlin: Springer (ISBN 978-3-642-29945-2/pbk). Lecture Notes in Computer Science 7188. Lecture Notes in Artificial Intelligence, 249-260 (2012). 2012 Berlin: Springer EN

doi:10.1007/978-3-642-29946-9_25

Summary: In the context of reinforcement learning, transfer learning refers to the concept of reusing knowledge acquired in past tasks to speed up the learning procedure in new tasks. Transfer learning methods have been succesfully applied in single-agent reinforcement learning algorithms, but no prior work has focused on applying them in a multi-agent environment. We propose a novel method for transfer learning in multi-agent reinforcement learning domains. We proceed to test the proposed approach in a multi-agent domain under various configurations. The results demonstrate that the method can reduce the learning time and increase the asymptotic performance of the learning algorithm.