Mixture of Expert Used to Learn Game Play
Mixture of Expert Used to Learn Game Play
复制标题
混合专家用于学习游戏玩法
DOI：
10.1007/978-3-540-87536-9_24
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
V. Kvasnicka
中科院分区：
文献类型：
--
作者：
P. Lacko;V. Kvasnicka
在本文中，我们研究了多智能体系统中的博弈策略的出现。符号和subsymbolic方法进行了比较。符号方法由具有指定搜索深度的回溯算法表示，而子符号方法由前馈神经网络表示，前馈神经网络由强化时间差TD（λ）技术自适应。我们研究了标准的前馈网络和自适应专家网络的混合。作为测试游戏，我们使用了简化的跳棋游戏。结果表明，这两个网络都能够游戏策略的出现。
In this paper, we study an emergence of game strategy in multiagent systems. Symbolic and subsymbolic approaches are compared. Symbolic approach is represented by a backtrack algorithm with specified search depth, whereas the subsymbolic approach is represented by feed-forward neural networks that are adapted by reinforcement temporal difference TD(λ) technique. We study standard feed-forward networks and mixture of adaptive experts networks. As a test game, we used the game of simplified checkers. It is demonstrated that both networks are capable of game strategy emergence.