Levente Kocsis

From Chessprogramming wiki
Revision as of 18:05, 3 June 2018 by GerdIsenberg (talk | contribs)
Jump to: navigation, search

Home * People * Levente Kocsis

Levente Kocsis [1]

Levente Kocsis,
a Hungarian computer scientist and researcher in Machine Learning with interests in Reinforcement Learning, Games like Chess, Go, Poker and Lines of Action, Search Control, Neural Networks and optimization algorithms for combinatorial problems. He defended his Ph.D thesis Learning Search Decisions [2] in 2003 at Maastricht University. Levente Kocsis is member of the Machine Learning Research Group of the Hungarian Academy of Sciences.

UCT

In 2006, along with Csaba Szepesvári, Levente Kocsis introduced UCT (Upper Confidence bounds applied to Trees), a new algorithm that applies bandit ideas to guide Monte-Carlo planning [3]. UCT accelerated the Monte-Carlo revolution in computer Go [4] and other domains.

Photos

Magog team smaller.jpg

The Magog team at the 7th Computer Olympiad 2002. Mark Winands, Levente Kocsis, Erik van der Werf [5]

Selected Publications

[6]

2000 ...

2005 ...

2010 ...

External Links

References

Up one level