EANT+KALMAN: An Efficient Reinforcement Learning Method for Continuous State Partially Observable Domains.

Yohannes Kassahun Jose de Gea Jan Hendrik Metzen Mark Edgington Frank Kirchner EANT+KALMAN: An Efficient Reinforcement Learning Method for Continuous State Partially Observable Domains. 241-248 2008 KI http://dx.doi.org/10.1007/978-3-540-85845-4_30 conf/ki/2008 db/conf/ki/ki2008.html#KassahunGMEK08