Kocsis Levente
Kocsis Levente
Verified email at sztaki.hu
TitleCited byYear
Bandit based monte-carlo planning
L Kocsis, C Szepesvári
Machine Learning: ECML 2006, 282-293, 2006
The grand challenge of computer Go: Monte Carlo tree search and extensions
S Gelly, L Kocsis, M Schoenauer, M Sebag, D Silver, C Szepesvári, ...
Communications of the ACM 55 (3), 106-113, 2012
Discounted ucb
L Kocsis, C Szepesvári
2nd PASCAL Challenges Workshop, 2006
Improved monte-carlo search
L Kocsis, C Szepesvári, J Willemson
Univ. Tartu, Estonia, Tech. Rep 1, 2006
Transpositions and move groups in Monte Carlo tree search
BE Childs, JH Brodeur, L Kocsis
Computational Intelligence and Games, 2008. CIG'08. IEEE Symposium On, 389-395, 2008
Efficient Multi-Start Strategies for Local Search Algorithms.
A György, L Kocsis
J. Artif. Intell. Res.(JAIR) 41, 407-444, 2011
Exploiting temporal influence in online recommendation
R Pálovics, AA Benczúr, L Kocsis, T Kiss, E Frigó
Proceedings of the 8th ACM Conference on Recommender systems, 273-280, 2014
Continuous Time Associative Bandit Problems.
A György, L Kocsis, I Szabó, C Szepesvári
IJCAI, 830-835, 2007
Universal parameter optimisation in games based on SPSA
L Kocsis, C Szepesvári
Machine Learning 63 (3), 249-286, 2006
RSPSA: enhanced parameter optimization in games
L Kocsis, C Szepesvári, MHM Winands
Advances in Computer Games, 39-56, 2006
Learning time allocation using neural networks
L Kocsis, J Uiterwijk, J van den Herik
Computers and Games, 170-185, 2001
Reduced-variance payoff estimation in adversarial bandit problems
L Kocsis, C Szepesvári
Proceedings of the ECML-2005 Workshop on Reinforcement Learning in Non …, 2005
Move ordering using neural networks
L Kocsis, J Uiterwijk, J van den Herik
Engineering of Intelligent Systems, 45-50, 2001
Learning in Lines of Action
MHM Winands, L Kocsis, JWHM Uiterwijk, HJ van den Herik
Temporal difference learning and the Neural MoveMap heuristic in the game of Lines of Action
MHM Winands, L Kocsis, J Uiterwijk, HJ van den Herik
GAME-ON, 99-103, 2002
Fully distributed robust singular value decomposition
I Hegedus, M Jelasity, L Kocsis, AA Benczúr
Peer-to-Peer Computing (P2P), 14-th IEEE International Conference on, 1-9, 2014
The neural movemap heuristic in chess
L Kocsis, JWHM Uiterwijk, E Postma, J van den Herik
Computers and Games, 154-170, 2003
Learning search decisions
L Kocsis
Universiteit Maastricht, 2003
Efficient multi-start strategies for local search algorithms
L Kocsis, A György
Machine Learning and Knowledge Discovery in Databases, 705-720, 2009
RecSys Challenge 2014: an ensemble of binary classifiers and matrix factorization
R Pálovics, F Ayala-Gómez, B Csikota, B Daróczy, L Kocsis, ...
Proceedings of the 2014 Recommender Systems Challenge, 13, 2014
The system can't perform the operation now. Try again later.
Articles 1–20