Preference-based evolutionary direct policy search
R. Busa-Fekete, B. Szörenyi, P. Weng, E. Hüllermeier, in: In Proceedings ECML/PKDD-Workshop on Reinforcement Learning from Generalized Feedback:Beyond Numerical Rewards, Prague, 2013.
Download
No fulltext has been uploaded.
Conference Paper
| English
Author
Busa-Fekete, Robert;
Szörenyi, B.;
Weng, P.;
Hüllermeier, EykeLibreCat
Department
Publishing Year
Proceedings Title
In Proceedings ECML/PKDD-Workshop on Reinforcement learning from Generalized Feedback:Beyond Numerical Rewards, Prague
LibreCat-ID
Cite this
Busa-Fekete R, Szörenyi B, Weng P, Hüllermeier E. Preference-based evolutionary direct policy search. In: In Proceedings ECML/PKDD-Workshop on Reinforcement Learning from Generalized Feedback:Beyond Numerical Rewards, Prague. ; 2013.
Busa-Fekete, R., Szörenyi, B., Weng, P., & Hüllermeier, E. (2013). Preference-based evolutionary direct policy search. In In Proceedings ECML/PKDD-Workshop on Reinforcement learning from Generalized Feedback:Beyond Numerical Rewards, Prague.
@inproceedings{Busa-Fekete_Szörenyi_Weng_Hüllermeier_2013, title={Preference-based evolutionary direct policy search}, booktitle={In Proceedings ECML/PKDD-Workshop on Reinforcement learning from Generalized Feedback:Beyond Numerical Rewards, Prague}, author={Busa-Fekete, Robert and Szörenyi, B. and Weng, P. and Hüllermeier, Eyke}, year={2013} }
Busa-Fekete, Robert, B. Szörenyi, P. Weng, and Eyke Hüllermeier. “Preference-Based Evolutionary Direct Policy Search.” In In Proceedings ECML/PKDD-Workshop on Reinforcement Learning from Generalized Feedback:Beyond Numerical Rewards, Prague, 2013.
R. Busa-Fekete, B. Szörenyi, P. Weng, and E. Hüllermeier, “Preference-based evolutionary direct policy search,” in In Proceedings ECML/PKDD-Workshop on Reinforcement learning from Generalized Feedback:Beyond Numerical Rewards, Prague, 2013.
Busa-Fekete, Robert, et al. “Preference-Based Evolutionary Direct Policy Search.” In Proceedings ECML/PKDD-Workshop on Reinforcement Learning from Generalized Feedback:Beyond Numerical Rewards, Prague, 2013.
Google Scholar