Implicatures and Nested Beliefs in Approximate Decentralized-POMDPs
Adam P. Vogel, Christopher E. Potts, Dan Jurafsky · 2013
Conversational implicatures involve reasoning about multiply nested belief structures. This complexity poses significant challenges for computational models of conversation and cognition. We show that agents in the multi-agent Decentralized-POMDP reach implicature-rich interpretations simply as a by-product of the way they reason about each other to maximize joint utility. Our simulations involve a reference game of the sort studied in psychology and linguistics as well as a dynamic, interactional scenario involving implemented artificial agents. 1