%0 Book Section %T Transfer in Reinforcement Learning: a Framework and a Survey %+ Sequential Learning (SEQUEL) %A Lazaric, Alessandro %B Reinforcement Learning - State of the art %E Marco Wiering, Martijn van Otterlo %I Springer %V 12 %P 143-173 %8 2012 %D 2012 %R 10.1007/978-3-642-27645-3_5 %Z Statistics [stat]/Machine Learning [stat.ML]Book sections %X Transfer in reinforcement learning is a novel research area that focuses on the development of methods to transfer knowledge from a set of source tasks to a target task. Whenever the tasks are \textit{similar}, the transferred knowledge can be used by a learning algorithm to solve the target task and significantly improve its performance (e.g., by reducing the number of samples needed to achieve a nearly optimal performance). In this chapter we provide a formalization of the general transfer problem, we identify the main settings which have been investigated so far, and we review the most important approaches to transfer in reinforcement learning. %G English %2 https://inria.hal.science/hal-00772626/document %2 https://inria.hal.science/hal-00772626/file/transfer.pdf %L hal-00772626 %U https://inria.hal.science/hal-00772626 %~ UNIV-LILLE3 %~ CNRS %~ INRIA %~ INRIA-LILLE %~ LAGIS %~ OPENAIRE %~ INRIA_TEST %~ TESTALAIN1 %~ INRIA2