Relational reinforcement learning (RRL) is a Q-learning technique which uses first order regression techniques to generalize the Qfunction. Both the relational setting and the Q-l...
— We present an algorithm for learning 3D object models from partial object observations. The input to our algorithm is a sequence of 3D laser range scans. Models learned from th...
Michael Ruhnke, Bastian Steder, Giorgio Grisetti, ...
Face representation based on the Visual Codebook becomes popular because of its excellent recognition performance, in which the critical problem is how to learn the most efficien...
As organization-based multiagent systems are applied to more complex problems, configuring and tuning the systems can become nearly as complex as the original problem a system wa...
Scott J. Harmon, Scott A. DeLoach, Robby, Doina Ca...
— Classic adaptive control methods for handling varying loads rely on an analytically derived model of the robot’s dynamics. However, in many situations, it is not feasible or ...