Home * People * Yasuhiro Osaki

Yasuhiro Osaki,
a Japanese computer scientist at Department of Computer Science, Tokyo University of Agriculture and Technology, affiliated with the laboratory of professor Yoshiyuki Kotani. His research interest includes reinforcement learning and the application of TD(λ) based on Monte-Carlo simulations in computer games. The program committee of the 12th Game Programming Workshop 2007 gave the best presentation award to Yasuhiro Osaki on TD(λ)-MC : A reinforcement learning with Monte-carlo simulations ^{[1] [2]}.

Selected Publications

• Yasuhiro Osaki, Kazutomo Shibahara, Yasuhiro Tajima, Yoshiyuki Kotani (2007). Reinforcement Learning of Evaluation Functions Using Temporal Difference-Monte Carlo learning method. 12th Game Programming Workshop
• Yasuhiro Osaki, Kazutomo Shibahara, Yasuhiro Tajima, Yoshiyuki Kotani (2008). An Othello Evaluation Function Based on Temporal Difference Learning using Probability of Winning. CIG'08, pdf
• Yasuhiro Osaki, Yoshiyuki Kotani (2009). A Learning Method of Evaluation Function Based on Selective Simulations. 14th Game Programming Workshop

References

1. ^ Yasuhiro Osaki, Kazutomo Shibahara, Yasuhiro Tajima, Yoshiyuki Kotani (2007). Reinforcement Learning of Evaluation Functions Using Temporal Difference-Monte Carlo learning method. 12th Game Programming Workshop, pdf (Japanese)
2. ^ TD-Lamda from Wikipedia

What links here?

Up one level