arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.05151cs.GTmath.OC
收藏

熵对策的算子方法

The operator approach to entropy games

Marianne Akian, Stéphane Gaubert, Julien Grand-Clément, Jérémie Guillaud

摘要:

熵博弈和矩阵乘法博弈最近已被Asarin等人引入。他们模拟的情况下,其中一个玩家(暴君)希望最小化的矩阵产品的增长率,而另一个玩家(论坛)希望最大化它。我们开发了一个运营商的熵博弈方法。这使我们能够表明,熵游戏可以铸造为随机平均支付游戏,其中一些行动空间是单纯形和支付的相对熵(Kullback-Leibler分歧)。通过这种方式,我们证明了具有固定数量的状态属于暴君的熵博弈可以在多项式时间内求解。这种方法也使我们能够解决这些游戏的政策迭代算法,我们比较光谱单纯形算法开发的Protasov。

英文摘要:

Entropy games and matrix multiplication games have been recently introduced by Asarin et al. They model the situation in which one player (Despot) wishes to minimize the growth rate of a matrix product, whereas the other player (Tribune) wishes to maximize it. We develop an operator approach to entropy games. This allows us to show that entropy games can be cast as stochastic mean payoff games in which some action spaces are simplices and payments are given by a relative entropy (Kullback-Leibler divergence). In this way, we show that entropy games with a fixed number of states belonging to Despot can be solved in polynomial time. This approach also allows us to solve these games by a policy iteration algorithm, which we compare with the spectral simplex algorithm developed by Protasov.

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。

↑