1     2     3     4     5     6     7     8     9     10     11     12    

P. Geibel (2007): Reinforcement Learning for Constrained MDPs. International Journal of Computational Intelligence Research -- Special issue on ICONIP 2006, Volume 3, Issue 1, pages 16-20.

Gust, H., Kühnberger, K.-U. & Geibel, P. (2007): Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory, in P. Hitzler & B. Hammer (eds.): Perspectives of Neural-Symbolic Integration, Studies in Computational Intelligence (SCI) 77, Springer, pp. 233-264


P. Geibel: Risk-Sensitive Approaches for Reinforcement Learning. Shaker-Verlag, 2006. PDF (230 pages)

P. Geibel (2006): Reinforcement Learning for MDPs with Constraints. In: H. Fürnkranz, T. Scheffer, and M. Spiliopoulou, editors, Proceedings of the ECML 2006, pages 646-653. Lecture Notes in Computer Science 4212, Springer. PDF

F. Wysotzki, and P. Geibel: Computer Supported Decision Making with Object Dependent Costs for Misclassification. In: Hommel, Günter., Sheng, Huanye (Eds): Human Interaction with Machines, Springer, 2006.


P. Geibel and Wysotzki. F.: Risk-Sensitive Learning Applied to Control &er Constraints. Journal of AI Research, vol. 24, pp. 81-108, 2005. PDF

A. Bendadi, O. Benn, P. Geibel, M. Hudik, T. Knebel, and F. Wysotzki: Lernen von Entscheidungsbaeumen bei objektabhaengigen Fehlklassifikationskosten. TU Berlin, Report No. 2004-18, 2005. ISSN 1436-9915.