“…Finite-state controllers explicitly represent infinite-horizon policies, but can also be used (as a possibly more concise representation) for finite horizon policies. They have been widely used in POMDPs 1 (e.g., see Kaelbling et al 1998, Hansen 1998, Meuleau et al 1999b, Poupart and Boutilier 2004, Poupart 2005, Toussaint et al 2006, 2008, Grześ et al 2013, Bai et al 2014 and Dec-POMDPs (e.g., Bernstein et al 2005, Amato et al 2007a, Bernstein et al 2009, Kumar and Zilberstein 2010b, Pajarinen and Peltonen 2011a, Kumar et al 2011, Pajarinen and Peltonen 2011b, Wu et al 2013.…”