-
摘要: 将Q-learning从单智能体框架上扩展到非合作的多智能体框架上,建立了在一般和随 机对策框架下的多智能体理论框架和学习算法,提出了以Nash平衡点作为学习目标.给出了对 策结构的约束条件,并证明了在此约束条件下算法的收敛性,对多智能体系统的研究与应用有 重要意义.
-
关键词:
- 多智能体 /
- Q-learning /
- 随机对策 /
- Nash平衡点
Abstract: Q-learning from original single-agent framework is extended to non-cooperative multi-agent framework, and the theoretic framework of multi-agent learning is proposed under general-sum stochastic games with Nash equilibrium point as learning objective. We introduce a multi-agent Q-learning algorithm and prove its convergence under certain restriction, which is very important for the study and application of multi-agent system.-
Key words:
- Multi-agent /
- Q-learning /
- stochadtic games /
- Nash equilibrium point
计量
- 文章访问数: 2062
- HTML全文浏览量: 196
- PDF下载量: 1057
- 被引次数: 0