\input zb-basic
\input zb-ioport
\iteman{io-port 06069364}
\itemau{Snel, Matthijs; Whiteson, Shimon}
\itemti{Multi-task reinforcement learning: shaping and feature selection.}
\itemso{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, 237-248 (2012).}
\itemab
Summary: Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced source tasks to speed up learning on a new target task. Earlier work has not clearly motivated choices for the shaping function. This paper discusses and empirically compares several alternatives, and demonstrates that the most intuive one may not always be the best option. In addition, we extend previous work on identifying good representations for the value and shaping functions, and show that selecting the right representation results in improved generalization over tasks.
\itemrv{~}
\itemcc{}
\itemut{}
\itemli{doi:10.1007/978-3-642-29946-9\_24}
\end