Evolving FPS Game Players by Using Continuous EDA-RL
Evolving FPS Game Players by Using Continuous EDA-RL
复制标题
DOI：
--
复制
发表时间：
2009-11
期刊：
影响因子：
--
通讯作者：
H. Tsubota;H. Handa
中科院分区：
文献类型：
--
作者：
H. Tsubota;H. Handa
本文将强化学习问题的分布估计算法EDA-RL推广到连续域。扩展的EDA-RL用于构建FPS游戏玩家。为了科普连续的输入输出关系，高斯网络被用于EBNA。在FPS游戏Unreal Tournament 2004上的仿真结果验证了该方法的有效性。
This paper extends EDA-RL, Estimation of Distribution Algorithms for Reinforcement Learning Problems, to continuous domain. The extended EDA-RL is used to constitiute FPS game players. In order to cope with continuous input-output relations, Gaussian Network is employed as in EBNA. Simulation results on Unreal Tournament 2004, one of major FPS games, confirm the effectiveness of the proposed method.