Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
Trevor Walker, Lisa Torrey, Jude W. Shavlik, Richa...
The mobile devices have gained much functionality and intelligence with the growth of network technologies, the abundance of network resources, and the increase of various services...
A new generation of intelligent applications can be enabled by broad-coverage knowledge repositories about everyday objects. We distill lessons in design of intelligent user inter...
Multi-agent systems are an attractive approach to modeling systems of interacting entities, but in some cases mathematical models of these systems can offer complementary benefits...
cting knowledge base can be seen abstractly as a set of arguments and a binary relation characterising conflict among them. There may be multiple plausible ways to evaluate confli...