Sensorimotor data from many interesting physical interactions comprises discontinuities. While existing locally weighted learning approaches aim at learning smooth functions, we p...
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
This paper shows how a text classifier's need for labeled training documents can be reduced by taking advantage of a large pool of unlabeled documents. We modify the Query-by...
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
Explanation-Based Reinforcement Learning (EBRL) was introduced by Dietterich and Flann as a way of combining the ability of Reinforcement Learning (RL) to learn optimal plans with...