An extension of a hierarchical reinforcement learning algorithm for multiagent settings

Abstract

This paper compares and investigates single-agent reinforcement learning (RL) algorithms on the simple and an extended taxi problem domain, and multiagent RL algorithms on a multiagent extension of the simple taxi problem domain we created. In particular, we extend the Policy Hill Climbing (PHC) and the Win or Learn Fast-PHC (WoLF-PHC) algorithms by combining them with the MAXQ hierarchical decomposition and investigate their efficiency. The results are very promising for the multiagent domain as they indicate that these two newly-created algorithms are the most efficient ones from the algorithms we compared. © 2012 Springer-Verlag.