task libraries, machine learning
Recent research in task transfer and task clustering has necessitated the need for task similarity measures in reinforcement learning. Determining task similarity is necessary for selective transfer where only information from relevant tasks and portions of a task are transferred. Which task similarity measure to use is not immediately obvious. It can be shown that no single task similarity measure is uniformly superior. The optimal task similarity measure is dependent upon the task transfer method being employed. We define similarity in terms of tasks, and propose several possible task similarity measures, dT, dp, dQ, and dR which are based on the transfer time, policy overlap, Q-values, and reward structure respectively. We evaluate their performance in three separate experimental situations.
Original Publication Citation
James Carroll and Kevin Seppi. "Task Similarity Measures for Transfer in Reinforcement Learning Task Libraries." In Proceedings of the International Joint Conference on Neural Networks, 25 pp. 83-88, Montreal, Canada.
BYU ScholarsArchive Citation
Carroll, James and Seppi, Kevin, "Task Similarity Measures for Transfer in Reinforcement Learning Task Libraries" (2005). Faculty Publications. 1007.
Physical and Mathematical Sciences
© 2005 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Copyright Use Information