The Association for the Advancement of Artificial Intelligence (AAAI) has selected the 1994 paper Acting Optimally in Partially Observable Stochastic Domains by Anthony R. Cassandra, Leslie Pack Kaelbling, and Michael Littman, then a Brown CS graduate student, for a 2013 AAAI Classic Paper Award. This award was established in 1999 to honor author(s) of paper(s) deemed most influential from a specific conference year. This year's award recognizes papers from the Twelfth National Conference on Artificial Intelligence that took place in 1994 in Seattle, Washington.
“Back in 1994, we were fascinated by the idea that an agent can make optimal decisions in spite of not knowing all the facts,” stated Michael Littman. “The math was originally developed in the operations research community, but we found that it was a perfect fit for the kinds of problems AI people are interested in addressing. These days, the notion of partial observability is a standard part of the AI vernacular.”
In academia a 'classic paper' is one that changes the direction of the field, typically because it identifies a “sweet spot”—a place where one can accomplish a lot without incurring overwhelming complexity. This paper is a classic "classic paper," added Professor Eugene Charniak.Michael Littman