Difference between revisions of "Naoki Mizukami"
GerdIsenberg (talk | contribs) (Created page with "'''Home * People * Naoki Mizukami''' '''Naoki Mizukami''', a Japanese computer scientist affiliated with the Graduate School of Engineering, [https://en.wik...") |
GerdIsenberg (talk | contribs) |
||
Line 1: | Line 1: | ||
'''[[Main Page|Home]] * [[People]] * Naoki Mizukami''' | '''[[Main Page|Home]] * [[People]] * Naoki Mizukami''' | ||
− | '''Naoki Mizukami''', | + | '''Naoki Mizukami''',<br/> |
a Japanese computer scientist affiliated with the Graduate School of Engineering, [https://en.wikipedia.org/wiki/University_of_Tokyo University of Tokyo]. His research interests include [[Monte-Carlo Tree Search|Monte-Carlo tree search]] and [[UCT]] considering [[Opponent Model Search|opponent models]], in particular applied to the game of [[Mahjong]] <ref>[[Naoki Mizukami]], [[Yoshimasa Tsuruoka]] ('''2015'''). ''Building a Computer Mahjong Player Based on Monte Carlo Simulation and Opponent Models''. [[IEEE#TOCIAIGAMES|IEEE CIG 2015]], [http://www.logos.ic.i.u-tokyo.ac.jp/~mizukami/paper/cig_2015.pdf pdf]</ref>, and [[Deep Learning|deep learning]]. | a Japanese computer scientist affiliated with the Graduate School of Engineering, [https://en.wikipedia.org/wiki/University_of_Tokyo University of Tokyo]. His research interests include [[Monte-Carlo Tree Search|Monte-Carlo tree search]] and [[UCT]] considering [[Opponent Model Search|opponent models]], in particular applied to the game of [[Mahjong]] <ref>[[Naoki Mizukami]], [[Yoshimasa Tsuruoka]] ('''2015'''). ''Building a Computer Mahjong Player Based on Monte Carlo Simulation and Opponent Models''. [[IEEE#TOCIAIGAMES|IEEE CIG 2015]], [http://www.logos.ic.i.u-tokyo.ac.jp/~mizukami/paper/cig_2015.pdf pdf]</ref>, and [[Deep Learning|deep learning]]. | ||
Latest revision as of 14:47, 8 August 2018
Home * People * Naoki Mizukami
Naoki Mizukami,
a Japanese computer scientist affiliated with the Graduate School of Engineering, University of Tokyo. His research interests include Monte-Carlo tree search and UCT considering opponent models, in particular applied to the game of Mahjong [1], and deep learning.
Selected Publication
- Naoki Mizukami, Yoshimasa Tsuruoka (2015). Building a Computer Mahjong Player Based on Monte Carlo Simulation and Opponent Models. IEEE CIG 2015, pdf
- Naoki Mizukami, Jun Suzuki, Hirotaka Kameko, Yoshimasa Tsuruoka (2017). Exploration Bonuses Based on Upper Confidence Bounds for Sparse Reward Games. Advances in Computer Games 15
- Hirotaka Kameko, Jun Suzuki, Naoki Mizukami, Yoshimasa Tsuruoka (2017). Deep Reinforcement Learning with Hidden Layers on Future States. Computer Games Workshop at IJCAI 2017, pdf
- Keigo Kawamura, Naoki Mizukami, Yoshimasa Tsuruoka (2017). Neural Fictitious Self-Play in Imperfect Information Games with Many Players. Computer Games Workshop at IJCAI 2017, pdf
External Links
References
- ↑ Naoki Mizukami, Yoshimasa Tsuruoka (2015). Building a Computer Mahjong Player Based on Monte Carlo Simulation and Opponent Models. IEEE CIG 2015, pdf
- ↑ Publications of Yoshimasa Tsuruoka