arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1310.8613cs.GT
收藏

同时移动对策中蒙特卡罗树搜索的收敛性

Convergence of Monte Carlo Tree Search in Simultaneous Move Games

Viliam Lisý, Vojtěch Kovařík, Marc Lanctot, Branislav Bošanský

摘要:

研究了具有完全信息和同时行动的零和广式对策中的蒙特卡罗树搜索。我们提出了一个通用的模板MCTS算法,这些游戏,它可以被实例化的各种选择方法。我们正式证明,如果选择方法是$ε$ -Hannan一致的矩阵游戏,并满足额外的要求,探索,然后MCTS算法最终收敛到一个近似纳什均衡(NE)的扩展形式的游戏。我们经验评估这一说法使用后悔匹配和Exp 3作为随机生成的游戏和经验选择的最坏情况下的游戏的选择方法。我们证实了正式的结果,并表明,额外的MCTS变体也收敛到近似NE的评估游戏。

英文摘要:

We study Monte Carlo tree search (MCTS) in zero-sum extensive-form games with perfect information and simultaneous moves. We present a general template of MCTS algorithms for these games, which can be instantiated by various selection methods. We formally prove that if a selection method is $ε$-Hannan consistent in a matrix game and satisfies additional requirements on exploration, then the MCTS algorithm eventually converges to an approximate Nash equilibrium (NE) of the extensive-form game. We empirically evaluate this claim using regret matching and Exp3 as the selection methods on randomly generated games and empirically selected worst case games. We confirm the formal result and show that additional MCTS variants also converge to approximate NE on the evaluated games.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑