Difference between revisions of "Takuya Hiraoka"
GerdIsenberg (talk | contribs) |
(No difference)
|
Revision as of 22:39, 5 August 2020
Home * People * Takuya Hiraoka
Takuya Hiraoka,
a Japanese computer scientist affiliated with the NEC Data Science Research Laboratories.
He holds a B.Sc. in informatics from Kindai University in 2011, and a M.Sc. and Ph.D. in information science from Nara Institute of Science and Technology in 2013 and 2016 respectively [2].
His research interests include dialogue system, reinforcement learning and game theory, and computer Shogi.
Along with Takenobu Takizawa, Takeshi Ito and Kunihito Hoki, he published on Contemporary Computer Shogi [3].
Selected Publications
2014 ...
- Takuya Hiraoka, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura (2014). Reinforcement Learning of Cooperative Persuasive Dialogue Policies using Framing. COLING 2014
- Takenobu Takizawa, Takeshi Ito, Takuya Hiraoka, Kunihito Hoki (2015). Contemporary Computer Shogi. Encyclopedia of Computer Graphics and Games
- Takuya Hiraoka, Masaaki Tsuchida, Yotaro Watanabe (2017). Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings. arXiv:1708.00667
- Seydou Ba, Takuya Hiraoka, Takashi Onishi, Toru Nakata, Yoshimasa Tsuruoka (2018). Monte Carlo Tree Search with Scalable Simulation Periods for Continuously Running Tasks. arXiv:1809.02378
2020 ...
- Takuya Hiraoka, Takahisa Imagawa, Voot Tangkaratt, Takayuki Osa, Takashi Onishi, Yoshimasa Tsuruoka (2020). Meta-Model-Based Meta-Policy Optimization. arXiv:2006.02608