Reinforcement Learning in Large State Spaces
Reinforcement Learning in Large State Spaces
复制标题
大状态空间中的强化学习
DOI：
10.1007/978-3-540-45135-8_27
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
B. Manderick
中科院分区：
文献类型：
--
作者：
K. Tuyls;S. Maes;B. Manderick
大的状态空间和不完整的信息是多智能体系统学习中突出的两个问题。在本文中，我们通过结合使用决策树和贝叶斯网络 (BN) 来对环境和 Q 函数进行建模来解决这两个问题。模拟机器人足球被用作测试平台，因为智能体面临着巨大的状态空间和不完整的信息。这项研究的长期目标是定义允许代理在大规模多代理系统中学习的通用技术。
Large state spaces and incomplete information are two problems that stand out in learning in multi-agent systems. In this paper we tackle them both by using a combination of decision trees and Bayesian networks (BNs) to model the environment and the Q-function. Simulated robotic soccer is used as a testbed, since there agents are faced with both large state spaces and incomplete information. The long-term goal of this research is to define generic techniques that allow agents to learn in large-scaled multi-agent systems.