Relational Representations in Reinforcement Learning: Review and Open Problems

Otterlo van, Martijn (2002) Relational Representations in Reinforcement Learning: Review and Open Problems. In: ICML'02 Workshop on Development of Representations, 9 July 2002, Sydney, Austraulia.

Preview

PDF
137Kb

Abstract:	This paper is about representation in RL.We discuss some of the concepts in representation and generalization in reinforcement learning and argue for higher-order representations, instead of the commonly used propositional representations. The paper contains a small review of current reinforcement learning systems using higher-order representations, followed by a brief discussion. The paper ends with research directions and open problems.
Item Type:	Conference or Workshop Item
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/65334
Official URL:	http://demo.cs.brandeis.edu/icml02ws/otterlo.pdf
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page