Collaborated with:Y.Kotani Nobuo Inui Yasuhiro Osaki Yasuhiro Tajima
Talks about:function (2) win (2) percentag (1) strategi (1) sigmoid (1) probabl (1) othello (1) tempor (1) differ (1) combin (1)
Person: Kazutomo Shibahara
DBLP: Shibahara:Kazutomo
Contributed to:
20052008Wrote 3 papers:
- CIG-2005-ShibaharaIK #adaptation #game studies
- Adaptive Strategies of MTD-f for Actual Games (KS, NI, YK).
- CIG-2008-OsakiSTK #difference #evaluation #learning #probability #using
- An Othello evaluation function based on Temporal Difference Learning using probability of winning (YO, KS, YT, YK), pp. 205–211.
- CIG-2008-ShibaharaK #monte carlo #simulation
- Combining final score with winning percentage by sigmoid function in Monte-Carlo simulations (KS, YK), pp. 183–190.