欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对非确定马尔可夫环境下的多智能体系统，提出了一种新的多智能体Q学习算法．算法中通过对联合动作的统计来学习其它智能体的行为策略，并利用智能体策略向量的全概率分布保证了对联合最优动作的选择．同时对算法的收敛性和学习性能进行了分析．该算法在多智能体系统RoboCup中的应用进一步表明了算法的有效性与泛化能力．
英文摘要：
Due to the presence of other agents, the environment of multi-agent systems （MAS） cannot be simply treated as Markov decision processes （MDPs）. The current reinforcement learning algorithms which are based on MDPs must be reformed before it can be applicable to MAS. Based on an agent＇s independent learning ability this paper proposes a novel Q-learning algorithm for MAS -an agent learning other agents＇ action policies through observing the joint action. The policies of other agents are expressed as action probability distribution matrixes. A concise and yet useful updating method for the matrixes is proposed. The full joint probability of distribution matrixes guarantees the learning agent to choose his/her optimal action. The convergence and performance of the proposed algorithm are analyzed theoretically. When applied to RoboCup, our algorithm showed high learning efficiency and good generalization ability. Finally, we briefly point out some directions of multi-agent reinforcement learning.
同期刊论文项目
同项目期刊论文
Delay-dependent robust H-infinity control for discrete- time uncertain systems with time-varying sta
Intelligent integrated control of combustion process of coke oven based on determination of operatin
New distributed positioning algorithm based on centroid of circular belt for wireless sensor network
A fast LDL-factorization approach for large sparse positive definite system and its application to o
An improved robust stability and robust stabilization method for linear discrete-time uncertain syst
A quality-and-Quantity prediction model for lead-zinc sintering process baesd on state parameters an
期刊信息
位置：