L
Levente Kocsis
Researcher at Hungarian Academy of Sciences
Publications - 39
Citations - 3547
Levente Kocsis is an academic researcher from Hungarian Academy of Sciences. The author has contributed to research in topics: Recommender system & Online machine learning. The author has an hindex of 14, co-authored 39 publications receiving 3311 citations. Previous affiliations of Levente Kocsis include University of Szeged & Maastricht University.
Papers
More filters
Book ChapterDOI
Bandit based monte-carlo planning
Levente Kocsis,Csaba Szepesvári +1 more
TL;DR: In this article, a bandit-based Monte-Carlo planning algorithm is proposed for large state-space Markovian decision problems (MDPs), which is one of the few viable approaches to find near-optimal solutions.
Journal ArticleDOI
The grand challenge of computer Go: Monte Carlo tree search and extensions
Sylvain Gelly,Levente Kocsis,Marc Schoenauer,Michèle Sebag,David Silver,Csaba Szepesvári,Olivier Teytaud +6 more
TL;DR: This paper describes the leading algorithms for Monte-Carlo tree search and explains how they have advanced the state of the art in computer Go.
Improved Monte-Carlo Search
TL;DR: A new algorithm is introduced, UCT, which extends a bandit algorithm for Monte-Carlo search, and it is proven that the probability that the algorithm selects the correct move converges to 1.
Proceedings ArticleDOI
Transpositions and move groups in Monte Carlo tree search
TL;DR: From the experimental results, it is concluded that both exploiting the graph structure and grouping moves may contribute to an increase in the playing strength of game programs using UCT.
Journal ArticleDOI
Efficient Multi-Start Strategies for Local Search Algorithms
András György,Levente Kocsis +1 more
TL;DR: It is proved that at most a quadratic increase in the number of times the target function is evaluated is needed to achieve the performance of a local search algorithm started from the attraction region of the optimum.