We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-b...
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
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. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
Trevor Walker, Lisa Torrey, Jude W. Shavlik, Richa...
An agent must acquire internal representation appropriate for its task, environment, sensors. As a learning algorithm, reinforcement learning is often utilized to acquire the rela...