Abstraction and Knowledge Transfer in Reinforcement Learning

Abstract

AbstractThis chapter presents the state of the art in research on reinforcement learning with a focus on abstraction and transfer learning. Especially, the open questions of performance in large, continuous state spaces and knowledge transfer are worked out as central challenges of reinforcement learning with regard to applications in Sect. 3.1. In the following, three approaches to tackle these problems are investigated: value function approximation (Sect. 3.2), temporal abstraction (Sect. 3.3), and spatial abstraction (Sect. 3.4).KeywordsReinforcement LearningTransfer LearningTarget TaskPrimitive ActionDefense Advance Research Project AgencyThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.