Difference between revisions of "Ting-Han Wei"

From Chessprogramming wiki
Jump to: navigation, search
 
Line 26: Line 26:
 
* [[Ti-Rong Wu]], [[I-Chen Wu]], [[Guan-Wun Chen]], [[Ting-Han Wei]], [[Tung-Yi Lai]], [[Hung-Chun Wu]], [[Li-Cheng Lan]] ('''2017'''). ''Multi-Labelled Value Networks for Computer Go''. [https://arxiv.org/abs/1705.10701 arXiv:1705.10701]
 
* [[Ti-Rong Wu]], [[I-Chen Wu]], [[Guan-Wun Chen]], [[Ting-Han Wei]], [[Tung-Yi Lai]], [[Hung-Chun Wu]], [[Li-Cheng Lan]] ('''2017'''). ''Multi-Labelled Value Networks for Computer Go''. [https://arxiv.org/abs/1705.10701 arXiv:1705.10701]
 
* [[Hung Guei]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2018'''). ''Using 2048-like games as a pedagogical tool for reinforcement learning''. [[CG 2018]], [[ICGA Journal#40_3|ICGA Journal, Vol. 40, No. 3]]
 
* [[Hung Guei]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2018'''). ''Using 2048-like games as a pedagogical tool for reinforcement learning''. [[CG 2018]], [[ICGA Journal#40_3|ICGA Journal, Vol. 40, No. 3]]
 +
* [[Hsiao-Chung Hsieh]], [[Ti-Rong Wu]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2019'''). ''Net2Net Extension for the AlphaGo Zero Algorithm''. [[Advances in Computer Games 16]]
 
==2020 ...==
 
==2020 ...==
 
* [[Hung Guei]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2020'''). ''2048-like games for teaching reinforcement learning''. [[ICGA Journal#42_1|ICGA Journal, Vol. 42, No. 1]]
 
* [[Hung Guei]], [[Ting-Han Wei]], [[I-Chen Wu]] ('''2020'''). ''2048-like games for teaching reinforcement learning''. [[ICGA Journal#42_1|ICGA Journal, Vol. 42, No. 1]]

Latest revision as of 15:39, 1 December 2021

Home * People * Ting-Han Wei

Ting-Han Wei [1]

Ting-Han Wei, (Ting han Wei, Ting-han Wei)
a Taiwanese computer scientist affiliated with the Department of Computer Science at National Chiao Tung University, Hsinchu, and Ph.D. student under professor I-Chen Wu, working in his Computer Games and Intelligence Lab [2] on various game playing programs such as the successful Go playing program CGI. His research interests include search algorithms, in particular Job-level (JL) computing, a general distributed computing approach. In JL computing, a search tree is maintained by a client process, while search tree nodes are evaluated, expanded, or generated by leveraging game-playing programs. These node operations are encapsulated as coarse-grain jobs. Concrete best-first JL implementations perform Proof-Number Search (JL-PNS) and UCT (JL-UCT).

Photos

Olympiad2017Go13x13.jpg

20th Computer Olympiad, Leiden 2017, Medalists in 13x13 Go, Katsuki Ohto (Bronze for Julie),
Ting-Han Wei (Gold for CGI) and Hideki Kato (Silver for Zen ) [3]

Selected Publications

[4]

2013 ...

2015 ...

2020 ...

External Links

References

Up one Level