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 2406.08683cs.GT
收藏

同步增量支撑调整与元博弈求解:连续动作博弈的均衡求解框架

Simultaneous incremental support adjustment and metagame solving: An equilibrium-finding framework for continuous-action games

Carlos Martin, Tuomas Sandholm

AI总结:

针对连续动作多参与者博弈,本文改进双预言机算法,通过固定规模策略集及增量元博弈求解与最优响应调整,低内存地求得低可利用度的近似混合策略纳什均衡。

摘要:

我们提出了一个用于计算连续动作博弈近似混合策略纳什均衡的框架。它是对传统双预言机算法的改进,扩展到多参与者和连续动作空间。与以往方法不同,该框架为每位参与者维护基数固定的纯策略集,因此仅需常量内存。此外,它不要求在每次迭代中进行精确的元博弈求解,因为对于大型元博弈而言,这可能带来高昂的计算代价;同时也不要求在每次迭代中计算全局最优响应,因为对于高维动作空间和一般博弈,这可能计算成本高昂甚至不可处理。我们的方法增量地降低有限元博弈中策略组合的可利用度,将其推向纳什均衡;与此同时,它在完整博弈中增量改进对该策略组合作出最优响应的纯策略。我们在多种连续动作博弈上评估了该方法,结果表明其能够获得具有低可利用度的近似混合策略纳什均衡。

英文摘要:

We present a framework for computing approximate mixed-strategy Nash equilibria of continuous-action games. It is a modification of the traditional double oracle algorithm, extended to multiple players and continuous action spaces. Unlike prior methods, it maintains fixed-cardinality pure strategy sets for each player. Thus, unlike prior methods, only a constant amount of memory is necessary. Furthermore, it does not require exact metagame solving on each iteration, which can be computationally expensive for large metagames. Moreover, it does not require global best-response computation on each iteration, which can be computationally expensive or even intractable for high-dimensional action spaces and general games. Our method incrementally reduces the exploitability of the strategy profile in the finite metagame, pushing it toward Nash equilibrium. Simultaneously, it incrementally improves the pure strategies that best respond to this strategy profile in the full game. We evaluate our method on various continuous-action games, showing that it obtains approximate mixed-strategy Nash equilibria with low exploitability.

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。

↑