István Szita
István Szita,
a Hungarian computer scientist and software engineer at Google Zurich. He holds a Ph.D. from Eötvös Loránd University on reinforcement learning (RL) [1],
and was postdoctoral researcher at Maastricht University, the RL3 group [2] of Rutgers University, and the University of Alberta.
Beside RL, his research interests include games, and recurrent neural nets.
Selected Publications
2006 ...
- István Szita, András Lőrincz (2006). Learning Tetris Using the Noisy Cross-Entropy Method. Neural Computation 18, pdf [5]
- István Szita (2007). Rewarding Excursions: Extending Reinforcement Learning to Complex Domains. Ph.D. thesis, supervisor András Lőrincz, Eötvös Loránd University, pdf
- Guillaume Chaslot, Sander Bakkes, István Szita, Pieter Spronck (2008). Monte-Carlo Tree Search: A New Framework for Game AI. pdf
- Guillaume Chaslot, Mark Winands, István Szita, Jaap van den Herik. (2008). Cross-entropy for Monte-Carlo Tree Search. ICGA Journal, Vol. 31, No. 3, pdf
- István Szita, Marc Ponsen, Pieter Spronck (2008). Keeping Adaptive Game AI interesting. CGames 2008, pdf draft, pdf
- István Szita, András Lőrincz (2008). The Many Faces of Optimism: a Unifying Approach. ICML 2008, pdf [6]
- István Szita, Guillaume Chaslot, Pieter Spronck (2009). Monte-Carlo Tree Search in Settlers of Catan. Advances in Computer Games 12, pdf [7]
2010 ...
- István Szita, Csaba Szepesvári (2010). Model-based reinforcement learning with nearly tight exploration complexity bounds. ICML 2010
- István Szita, Csaba Szepesvári (2011). Agnostic KWIK learning and efficient approximate reinforcement learning. Journal of Machine Learning Research - Proceedings Track 19
- István Szita (2012). Reinforcement Learning in Games. in Marco Wiering, Martijn Van Otterlo (2012). Reinforcement learning: State-of-the-art. Adaptation, Learning, and Optimization, Vol. 12, Springer
- Thomas J. Walsh, István Szita, Carlos Diuk, Michael L. Littman (2012). Exploring compact reinforcement-learning representations with linear regression. arXiv:1205.2606
External Links
References
- ↑ István Szita (2007). Rewarding Excursions: Extending Reinforcement Learning to Complex Domains. Ph.D. thesis, supervisor András Lőrincz, Eötvös Loránd University, pdf
- ↑ RL3, Rutgers Laboratory for Real-Life Reinforcement Learning
- ↑ István Szita - Publications
- ↑ dblp: István Szita
- ↑ Tetris from Wikipedia
- ↑ The Many Faces of Optimism: a Unifying Approach - videolectures.net
- ↑ The Settlers of Catan from Wikipedia