• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Bioinspired Optimization Methods and Their Applications >Reinforcement Learning for N-player Games: The Importance of Final Adaptation
【24h】

Reinforcement Learning for N-player Games: The Importance of Final Adaptation

机译：N-Player游戏的强化学习：最终适应的重要性

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper covers n-tuple-based reinforcement learning (RL) algorithms for games. We present a new algorithm for temporal difference (TD) learning which works seamlessly on various games with arbitrary number of players. This is achieved by taking a player-centered view where each player propagates his/her rewards back to previous rounds. We add a new element called Final Adaptation RL (FARL) to this algorithm. Our main contribution is that FARL is a vitally important ingredient to achieve success with the player-centered view in various games. We report results on seven board games with 1, 2 and 3 players, including Othello, ConnectFour and Hex. In most cases it is found that FARL is important to learn a near-perfect playing strategy. All algorithms are available in the GBG framework on GitHub.
机译：本文涵盖了基于N组的加固学习（RL）算法。我们提出了一种新的时间差异（TD）学习算法，它在各种游戏中无缝地工作，具有任意数量的玩家。这是通过占据以球员为中心的观点来实现的，其中每个玩家将他/她的奖励传播到之前的轮次。我们将称为最终适应RL（Farl）的新元素添加到该算法。我们的主要贡献是，Farl是一项最重要的成分，可以在各种游戏中达到成功的成功。我们在七场比赛中举报结果，其中包括1,2和3名球员，包括奥赛罗，Connectfour和Hex。在大多数情况下，发现Farl非常重要，无法学习近乎完美的竞争策略。所有算法都在GitHub上的GBG框架中提供。

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