Abstract. Most of multi-agent reinforcement learning algorithms aim to converge to a Nash equilibrium, but a Nash equilibrium does not necessarily mean a desirable result. On the o...
Abstract. This paper studies the properties and performance of models for estimating local probability distributions which are used as components of larger probabilistic systems ā...
Kristina Toutanova, Mark Mitchell, Christopher D. ...
Abstract. Very often a planning problem can be formulated as a ranking problem: i.e. to ļ¬nd an order relation over a set of alternatives. The ranking of a ļ¬nite set of alternat...
Abstract. Ozaās Online Boosting algorithm provides a version of AdaBoost which can be trained in an online way for stationary problems. One perspective is that this enables the p...
Adam Pocock, Paraskevas Yiapanis, Jeremy Singer, M...
Abstract. In the constraint satisfaction problem (CSP), the aim is to ļ¬nd an assignment of values to a set of variables subject to speciļ¬ed constraints. In the minimum cost hom...