Reinforcement Learning for Relational MDPs

Otterlo van, Martijn (2004) Reinforcement Learning for Relational MDPs. In: Machine Learning Conference of Belgium and the Netherlands, BeNeLearn '04, 8-9 Jan 2004, Brussels, Belgium.

Preview

PDF
555Kb

Abstract:	In this paper we present a new method for reinforcement learning in relational domains. A logical language is employed to abstract over states and actions, thereby decreasing the size of the state-action space significantly. A probabilistic transition model of the abstracted Markov-Decision-Process is estimated to to speed-up learning. We present theoretical and experimental analysis of our new representation. Some insights concerning the problems and opportunities of logical representations for reinforcement learning are obtained in the context of a growing interest in the use of abstraction in reinforcement learning contexts.
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/64849
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 221212