“…Submodularity is an important property, because in cases where the VOI is submodular, simple, greedy algorithms result in provably near-optimal policies (Krause & Guestrin, 2009, 2011Papachristoudis & Fisher III, 2012). However, the VOI is not submodular in general (Radner & Stiglitz, 1984;Lara & Gilotte, 2007;Chadeand & Schlee, 2001;Krause & Guestrin, 2009), and in particular submodularity does not hold in the selection problem , even in a very limited case involving only two items. Other types of approximate solutions for the batch version of the selection problem exist (Reches, Gal, & Kraus, 2013), with theoretical bounds on the approximation error not based on submodularity.…”