arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.06341cs.GTcs.AIcs.LG
收藏

游戏中的策略教学

Strategic Teaching and Learning in Games

University of California, Davis(加州大学戴维斯分校)

Burkhard C. Schipper

摘要:

已知在所有有限博弈中存在导致纳什均衡的非耦合学习策略。为什么玩家应该使用这种学习启发式方法?它们从何而来?我们表明,没有解耦的学习启发式导致纳什均衡在所有有限的游戏,玩家有动机采取,这将是进化稳定的,或者可以“学习自己”。相反,一个参与者有动机在战略上教导这样一个学习对手,以确保至少Stackelberg领导者的回报。不可能的结果仍然完好无损时,限制类的一般游戏,两个球员的游戏,潜在的游戏,游戏与战略补充或2x2游戏,其中学习是已知的“好”。更一般地说,它也适用于非耦合学习算法,导致相关的均衡,合理化的结果,迭代可接受的结果,或最小遏制集。一个可能的结果限制在“战略平凡”的游戏失败,如果一些通用的游戏之外,这一类被认为是以及。

英文摘要:

It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should players use such learning heuristics and where could they come from? We show that there is no uncoupled learning heuristic leading to Nash equilibrium in all finite games that a player has an incentive to adopt, that would be evolutionary stable or that could "learn itself". Rather, a player has an incentive to strategically teach such a learning opponent in order secure at least the Stackelberg leader payoff. The impossibility result remains intact when restricted to the classes of generic games, two-player games, potential games, games with strategic complements or 2x2 games, in which learning is known to be "nice". More generally, it also applies to uncoupled learning heuristics leading to correlated equilibria, rationalizable outcomes, iterated admissible outcomes, or minimal curb sets. A possibility result restricted to "strategically trivial" games fails if some generic games outside this class are considered as well.

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。

↑