Efficiently Solving Turn-Taking Stochastic Games with Extensive-Form Correlation
Efficiently Solving Turn-Taking Stochastic Games with Extensive-Form Correlation
复制标题
有效解决具有广泛形式相关性的轮流随机博弈
DOI:
10.1145/3580507.3597665
复制
发表时间:
2023
期刊:
影响因子:
--
通讯作者:
Conitzer, Vincent
中科院分区:
文献类型:
--
作者:
Zhang, Hanrui;Cheng, Yu;Conitzer, Vincent
We study equilibrium computation with extensive-form correlation in two-player turn-taking stochastic games. Our main results are two-fold: (1) We give an algorithm for computing a Stackelberg extensive-form correlated equilibrium (SEFCE), which runs in time polynomial in the size of the game, as well as the number of bits required to encode each input number. (2) We give an efficient algorithm for approximately computing an optimal extensive-form correlated equilibrium (EFCE) up to machine precision, i.e., the algorithm achieves approximation errorεin time polynomial in the size of the game, as well as log(1/ε).Our algorithm for SEFCE is the first polynomial-time algorithm for equilibrium computation with commitment in such a general class of stochastic games. Existing algorithms for SEFCE typically make stronger assumptions such as no chance moves, and are designed for extensive-form games in the less succinct tree form. Our algorithm for approximately optimal EFCE is, to our knowledge, the first algorithm that achieves 3 desiderata simultaneously: approximate optimality, polylogarithmic dependency on the approximation error and compatibility with stochastic games in the more succinct graph form. Existing algorithms achieve at most 2 of these desiderata, often also relying on additional technical assumptions.
登录
查看更多内容
DOI:
--
发表时间:
2022
期刊:
NeurIPS
影响因子:
--
作者:
Zhang, B.;Sandholm, T.
通讯作者:
Sandholm, T.
DOI:
--
发表时间:
2022
期刊:
ICLR-22 Workshop on Gamification and Multiagent Solutions
影响因子:
--
作者:
Zhang, B.;Farina, G.;Celli, A.;Sandholm, T.
通讯作者:
Sandholm, T.
DOI:
--
发表时间:
2019
期刊:
Conference on Neural Information Processing Systems.
影响因子:
--
作者:
Farina, G;Ling, C K;Fang, F;Sandholm, T
通讯作者:
Sandholm, T
DOI:
--
发表时间:
2020
期刊:
Conference on Neural Information Processing Systems
影响因子:
--
作者:
Farina, G.;Sandholm, T.
通讯作者:
Sandholm, T.
DOI:
--
发表时间:
2008
期刊:
Games Econ. Behav.
影响因子:
--
作者:
Vincent Conitzer;T. Sandholm
通讯作者:
T. Sandholm