The application of Reinforcement Learning (RL) algorithms to learn tasks for robots is often limited by the large dimension of the state space, which may make prohibitive its appli...
Andrea Bonarini, Alessandro Lazaric, Marcello Rest...
Both reactive and deliberative qualities are essential for a good action selection mechanism. We present a model that embodies a hybrid of two very different neural network archit...
Abstract. In many cases, users may want to consider incomplete answers to their queries. Often, however, there is an overwhelming number of such answers, even if subsumed answers a...
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...
Earlier research on gender effects with software features intended to help problem-solvers in end-user debugging environments has shown that females are less likely to use unfamil...
Laura Beckwith, Cory Kissinger, Margaret M. Burnet...