Christian Wirth, Johannes Fürnkranz. A Policy Iteration Algorithm for Learning from Preference-Based Feedback. In Allan Tucker, Frank Höppner, Arno Siebes, Stephen Swift, editors, Advances in Intelligent Data Analysis XII - 12th International Symposium, IDA 2013, London, UK, October 17-19, 2013. Proceedings. Volume 8207 of Lecture Notes in Computer Science, pages 427-437, Springer, 2013. [doi]
@inproceedings{WirthF13, title = {A Policy Iteration Algorithm for Learning from Preference-Based Feedback}, author = {Christian Wirth and Johannes Fürnkranz}, year = {2013}, doi = {10.1007/978-3-642-41398-8_37}, url = {http://dx.doi.org/10.1007/978-3-642-41398-8_37}, researchr = {https://researchr.org/publication/WirthF13}, cites = {0}, citedby = {0}, pages = {427-437}, booktitle = {Advances in Intelligent Data Analysis XII - 12th International Symposium, IDA 2013, London, UK, October 17-19, 2013. Proceedings}, editor = {Allan Tucker and Frank Höppner and Arno Siebes and Stephen Swift}, volume = {8207}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-642-41397-1}, }