Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
Abstract— We consider the task of omnidirectional path following for a quadruped robot: moving a four-legged robot along any arbitrary path while turning in any arbitrary manner....
— We present a new motion planning framework that explicitly considers uncertainty in robot motion to maximize the probability of avoiding collisions and successfully reaching a ...
LOCATE is workspace layout design software that also serves as a testbed for developing and refining principles of adaptive aiding. This demonstration illustrates LOCATE's ab...
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...