INFORMATICA International Journal Main Page Editorial Board Abstracting/Indexing Instructions to Authors Subscription Information Contents Author Index Papers in Production		INFORMATICA, 2003, Vol. 14, No. 2, 237-250 © Institute of Mathematics and Informatics, ISSN 0868-4952 Efficient Exploration in Reinforcement Learning Based on Utile Suffix Memory Arthur PCHELKIN Faculty of Computer Science and Information Technology Riga Technical University 1 Kalku Str., LV-1658 Riga, Latvia E-mail: arturp@balticom.lv Abstract Reinforcement learning addresses the question of how an autonomous agent can learn to choose optimal actions to achieve its goals. Efficient exploration is of fundamental importance for autonomous agents that learn to act. Previous approaches to exploration in reinforcement learning usually address exploration in the case when the environment is fully observable. In contrast, we study the case when the environment is only partially observable. We consider different exploration techniques applied to the learning algorithm ``Utile Suffix Memory'', and, in addition, discuss an adaptive fringe depth. Experimental results in a partially observable maze show that exploration techniques have serious impact on performance of learning algorithm. Keywords: reinforcement learning, exploration, hidden state, short-term memory To preview Lithuanian abstract see full article text To preview full article text in PDF format click here You could obtain free Acrobat Reader from Adobe
Top		Copyright © INFORMATICA, Vilnius University Institute of Mathematics and Informatics, 2010