By learning a range of possible times over which the effect of an action can take place, a robot can reason more effectively about causal and contingent relationships in the world...
We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in comp...
Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa...
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Wei...
Abstract. Autonomous exploration is a frequently addressed problem in the robotics community. This paper presents an approach to mobile robot exploration that takes into account th...
Dominik Joho, Cyrill Stachniss, Patrick Pfaff, Wol...
Abstract. Learning Object Metadata (LOM) is an interoperable standard focused on enabling the reuse of learning material for authoring lessons. Nevertheless, few work was done on t...