Bellman goes Relational

Kersting, Kristian and Otterlo van, Martijn and De Raedt, Luc (2004) Bellman goes Relational. In: 21st International Conference on Machine Learning, ICML 2004, 5 July 2004, Banff, Alberta, Canada.

Preview

PDF
220Kb

Abstract:	Motivated by the interest in relational reinforcement learning, we introduce a novel relational Bellman update operator called ReBel. It employs a constraint logic programming language to compactly represent Markov decision processes over relational domains. Using ReBel, a novel value iteration algorithm is developed in which abstraction (over states and actions) plays a major role. This framework provides new insights into relational reinforcement learning. Convergence results as well as experiments are presented.
Item Type:	Conference or Workshop Item
Copyright:	© 2004 ACM
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/64847
Official URL:	http://dx.doi.org/10.1145/1015330.1015401
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 221179