| TD-BP强化学习算法在五子棋博弈系统中的应用 |
| |
| 引用本文： | 宫瑞敏,吕艳辉.TD-BP强化学习算法在五子棋博弈系统中的应用[J].沈阳理工大学学报,2010,29(4):30-32,37. |
| |
| 作者姓名： | 宫瑞敏 吕艳辉 |
| |
| 作者单位： | 沈阳理工大学信息科学与工程学院,辽宁沈阳110159 |
| |
| 摘 要： | 局面估值的准确性是决定棋类游戏水平高低的一个重要因素。针对使用静态估值函数的不足,提出了TD-BP强化学习算法,结合博弈中常用的极小极大搜索算法和经过历史启发增强的PVS搜索算法,实现了一种自适应性较强的五子棋自学习程序。实验结果表明,使用该算法的程序经过较短时间的训练后达到了较好的下棋水平.
|
| 关 键 词： | TD算法 BP神经网络 估值函数 PVS算法 |
Applications of TD-BP Algorithm in Renju Game System |
| |
| GONG Rui-min,LV Yan-hui.Applications of TD-BP Algorithm in Renju Game System[J].Transactions of Shenyang Ligong University,2010,29(4):30-32,37. |
| |
| Authors: | GONG Rui-min LV Yan-hui |
| |
| Affiliation: | (Shenyang Ligong University,Shenyang 110159,China) |
| |
| Abstract: | The accuracy of the valuations is one of the important factors which decide the chess games＇ level.For the fact that static valuations function is rarely used,reinforcement learning algorithm of TD-algorithm combined with BP neural network is proposed.Based on common mini-max search algorithm and PVS search algorithm enhanced by history heuristic,the self-study ability of Renju Game program is realized.Experimental results showed this method of the program achieves a good chess level after a short time training. |
| |
| Keywords: | TD algorithm BP neural network valuations function PVS algorithm |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
