D-CIS Publication Database

van Seijen, Harm    

Firstname:Harm 
von:van 
Surname:Seijen 
Initials:H. 
Email:hamr.vanseijen@tno.nl 
Institute:TNO Defence, Security and Safety 
Homepage: 

4 publications

2 Keywords relate to this author

Multiple qualitatively different state representations
Reinforcement learning




Publications as Author



2009

van Seijen, Harm and Whiteson, Shimon, Postponed Updates for Temporal-Difference Reinforcement Learning, in: Proceedings of the International Conference on Intelligent Systems Design and Applications, 2009.
 
van Seijen, Harm, van Hasselt, Hado, Whiteson, Shimon and Wiering, Marco, A Theoretical and Empirical Analysis of Expected Sarsa, in: ADPRL 2009: Proceedings of the IEEE Symposium on Adaptive Programming and Reinforcement Learning, 2009.
 

2008

van Seijen, Harm, Bakker, Bram and Kester, Leon, Switching between Different State Representations in Reinforcement Learning, in: Proceedings of the Artificial Intelligence and Applications Conference, 2008.
 

2007

van Seijen, Harm, Bakker, Bram and Kester, Leon, Reinforcement Learning with Multiple, Qualitatively Different State Representations, in: NIPS workshop Hierarchical methods, Vancouver, Canada, 2007.