Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
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...
Grasping an object is a task that inherently needs to be treated in a hybrid fashion. The system must decide both where and how to grasp the object. While selecting where to grasp...
— Localization for low cost humanoid or animal-like personal robots has to rely on cheap sensors and has to be robust to user manipulations of the robot. We present a visual loca...
We present progress with roBlocks, a reconfigurable modular robotic system for education. Children snap together small, magnetic, heterogeneous modules to create larger, more comp...