Difference between revisions of "Csaba Szepesvári"

From Chessprogramming wiki
Jump to: navigation, search
Line 34: Line 34:
 
* [[Tor Lattimore]], [[Csaba Szepesvári]] ('''2017'''). ''The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits''.  [https://www.aistats.org/aistats2017/ AISTATS], [https://sites.ualberta.ca/~szepesva/papers/linbandits_aistats17.pdf pdf]
 
* [[Tor Lattimore]], [[Csaba Szepesvári]] ('''2017'''). ''The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits''.  [https://www.aistats.org/aistats2017/ AISTATS], [https://sites.ualberta.ca/~szepesva/papers/linbandits_aistats17.pdf pdf]
 
* [[Tor Lattimore]], [[Csaba Szepesvári]] ('''2018'''). ''Cleaning up the neighborhood: A full classification for adversarial partial monitoring''. [https://arxiv.org/abs/1805.09247 arXiv:1805.09247]
 
* [[Tor Lattimore]], [[Csaba Szepesvári]] ('''2018'''). ''Cleaning up the neighborhood: A full classification for adversarial partial monitoring''. [https://arxiv.org/abs/1805.09247 arXiv:1805.09247]
 +
* [[Tor Lattimore]], [[Csaba Szepesvári]] ('''2019'''). ''Bandit Algorithms''. Cambridge University Press (draft), [http://downloads.tor-lattimore.com/banditbook/book.pdf pdf]
  
 
=External Links=  
 
=External Links=  
Line 44: Line 45:
 
=References=  
 
=References=  
 
<references />
 
<references />
 
 
'''[[People|Up one level]]'''
 
'''[[People|Up one level]]'''
 +
[[Category:Researcher|Szepesvári]]

Revision as of 22:46, 12 February 2019

Home * People * Csaba Szepesvári

Csaba Szepesvári [1]

Csaba Szepesvári,
a Hungarian computer scientiest with research interests in applications of statistical techniques in AI, and Reinforcement Learning [2]. Csaba Szepesvári worked at the Computer and Automation Research Institute of the Hungarian Academy of Sciences, and is professor at the Department of Computing Science, University of Alberta, and principal investigator of the RLAI [3] group, actually on leave at DeepMind.

UCT

In 2006, along with Levente Kocsis, Csaba Szepesvári introduced UCT (Upper Confidence bounds applied to Trees), a new algorithm that applies bandit ideas to guide Monte-Carlo planning [4]. UCT accelerated the Monte-Carlo revolution in computer Go [5] and other domains.

Selected Publications

[6] [7]

1994 ...

2005 ...

2010 ...

2015 ...

External Links

References

Up one level