Speeding-up reinforcement learning through abstraction and transfer learning

Abstract

We are interested in the following general question: is it pos- sible to abstract knowledge that is generated while learning the solution of a problem, so that this abstraction can ac- celerate the learning process? Moreover, is it possible to transfer and reuse the acquired abstract knowledge to ac- celerate the learning process for future similar tasks? We propose a framework for conducting simultaneously two lev- els of reinforcement learning, where an abstract policy is learned while learning of a concrete policy for the problem, such that both policies are refined through exploration and interaction of the agent with the environment. We explore abstraction both to accelerate the learning process for an op- timal concrete policy for the current problem, and to allow the application of the generated abstract policy in learning solutions for new problems. We report experiments in a robot navigation environment that show our framework to be effective in speeding up policy construction for practical problems and in generating abstractions that can be used to accelerate learning in new similar problems.