2007 | ||
---|---|---|
2 | EE | Yugo Hasegawa, Satoko Takada, Hidehiro Nakano, Shuichi Arai, Arata Miyauchi: A reinforcement learning method using a dynamic reinforcement function based on action selection probability. Systems and Computers in Japan 38(7): 1-11 (2007) |
1999 | ||
1 | EE | Shuichi Arai: Integrated knowledge description of image and language to acquire the concept of linguistic symbol standing for shape and structure through learning. Systems and Computers in Japan 30(9): 44-54 (1999) |
1 | Yugo Hasegawa | [2] |
2 | Arata Miyauchi | [2] |
3 | Hidehiro Nakano | [2] |
4 | Satoko Takada | [2] |