My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
Information on site-specific spectrum characteristics is essential to evaluate and improve the performance of wireless networks. However, it is usually very costly to obtain accur...
Abstract— We consider the problem of optimizing the trajectory of a mobile sensor with perfect localization whose task is to estimate a stochastic, perhaps multidimensional fiel...
This study describes how complex goal-directed behavior can evolve in a hierarchically organized recurrent neural network controlling a simulated Khepera robot. Different types of ...
Abstract— Mobile robots need maps or other forms of geometric information about the environment to navigate. The mobility sensors (LADAR, stereo, etc.) on these robotic vehicles ...
Bart C. Nabbe, Derek Hoiem, Alexei A. Efros, Marti...