首页> 外文期刊>Computational Intelligence and AI in Games, IEEE Transactions on >An Automatically Generated Evaluation Function in General Game Playing
【24h】

An Automatically Generated Evaluation Function in General Game Playing

机译:一般游戏中自动生成的评估功能

获取原文
获取原文并翻译 | 示例
           

摘要

General game-playing (GGP) competitions provide a framework for building multigame-playing agents. In this paper, we describe an attempt at the implementation of such an agent. It relies heavily on our knowledge-free method of automatic construction of an approximate state evaluation function, based on game rules only. This function is then employed by one of the two game tree search methods: MTD$(f)$ or guided upper confidence bounds applied to trees (GUCT), the latter being our proposal of an algorithm combining UCT with the usage of an evaluation function. The performance of our agent is very satisfactory when compared to a baseline UCT implementation.
机译:<?Pub Dtl?>常规游戏(GGP)竞赛提供了一个用于构建多游戏代理的框架。在本文中,我们描述了实现这种代理的尝试。它严重依赖于我们仅基于游戏规则的无状态自动构建近似状态评估功能的方法。然后,两种游戏树搜索方法之一将使用此功能:MTD <公式ulatypetype =“ inline”> $(f)$ 或引导的置信上限应用于树木(GUCT),后者是我们提出的将UCT与评估函数结合使用的算法的建议。与基准UCT实施相比,我们的代理的性能非常令人满意。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号