.png){kind=icon}
返回
A Generalized Minimax Q-Learning Algorithm for Two-Player Zero-Sum Stochastic Games
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2022.3159453.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We consider the problem of two-player zero-sum games. This problem is formulated as a min-max Markov game in this article. The solution of this game, which is the min-max payoff, starting from a given state is called the min-max value of the state. In this article, we compute the solution of the two-player zero-sum game, utilizing the technique of successive relaxation that has been successfully applied in this article to compute a faster value iteration algorithm in the context of Markov decision processes. We extend the concept of successive relaxation to the setting of two-player zero-sum games. We show that, under a special structure on the game, this technique facilitates faster computation of the min-max value of the states. We then derive a generalized minimax Q-learning algorithm, which computes the optimal policy when the model information is not known. Finally, we prove the convergence of the proposed generalized minimax Q-learning algorithm utilizing stochastic approximation techniques, under an assumption on the boundedness of iterates. Through experiments, we demonstrate the
Keyword:
Games
Q-learning
Game theory
Markov processes
Convergence
Standards
Computational modeling
Minimax Q-learning
successive relaxation
two-player zero-sum games
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
.png){kind=icon}
没有更多内容
没有更多内容