FMR-GA -- A cooperative multi-agent reinformcement learning algorithm based on gradient ascent

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	FMR-GA -- A cooperative multi-agent reinformcement learning algorithm based on gradient ascent
	Zhen Zhang 1; Dongqing Wang 1; Dongbin Zhao2 ; Tingting Song 1
发表期刊	Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634)
	2017
期号	*页码:840–848
摘要	Gradient ascent methods combined with Multi-Agent Reinforcement Learning (MARL) have been studied for years as a potential direction to design new MARL algorithms. This paper proposes a gradient-based MARL algorithm – Frequency of the Maximal Reward based on Gradient Ascent (FMR-GA). The aim is to reach the maximal total reward in repeated games. To achieve this goal and simplify the stability analysis procedure, we have made effort in two aspects. Firstly, the probability of getting the maximal total reward is selected as the objective function, which simplifies the expression of the gradient and facilitates reaching the learning goal. Secondly, a factor is designed and is added to the gradient. This will produce the desired stable critical points corresponding to the optimal joint strategy. We propose a MARL algorithm called Probability of Maximal Reward based on Infinitsmall Gradient Ascent (PMR-IGA), and analyze its convergence in two-player two-action and two-player three-action repeated games. Then we derive a practical MARL algorithm FMR-GA from PMR-IGA. Theoretical and simulation results show that FMR-GA will converge to the optimal strategy in the cases presented in this paper
关键词	Reinforcement Learning Multi-agent Gradient Ascent Q-learning
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/19420
专题	多模态人工智能系统全国重点实验室_深度强化学习
作者单位	1.School of Automation and Electrical EngineeringQingdao UniversityQingdaoChina 2.State Key Laboratory of Management and Control for Complex Systems, Institute of AutomationChinese Academy of SciencesBeijingChina
推荐引用方式 GB/T 7714	Zhen Zhang,Dongqing Wang,Dongbin Zhao,et al. FMR-GA -- A cooperative multi-agent reinformcement learning algorithm based on gradient ascent[J]. Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634),2017(*):840–848.
APA	Zhen Zhang,Dongqing Wang,Dongbin Zhao,&Tingting Song.(2017).FMR-GA -- A cooperative multi-agent reinformcement learning algorithm based on gradient ascent.Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634)(*),840–848.
MLA	Zhen Zhang,et al."FMR-GA -- A cooperative multi-agent reinformcement learning algorithm based on gradient ascent".Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634) .*(2017):840–848.