Consider the task of exploring the Web in order to find pages of a particular kind or on a particular topic. This task arises in the construction of search engines and Web knowled...
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
Abstract— Reinforcement learning algorithms have been successfully applied in robotics to learn how to solve tasks based on reward signals obtained during task execution. These r...