A two-layered multi-agent reinforcement learning model and algorithm

doi:10.1016/j.jnca.2006.09.004

A two-layered multi-agent reinforcement learning model and algorithm

2007-11-01

18

PRE

AI

DOI：10.1016/j.jnca.2006.09.004

原文链接

原文求助

摘要

En 中文

Multi-agent reinforcement learning technologies are mainly investigated from two perspectives of the concurrence and the game theory. The former chiefly applies to cooperative multi-agent systems, while the latter usually applies to coordinated multi-agent systems. However, there exist such problems as the credit assignment and the multiple Nash equilibriums for agents with them. In this paper, we propose a new multi-agent reinforcement learning model and algorithm LMRL from a layer perspective. LMRL model is composed of an off-line training layer that employs a single agent reinforcement learning technology to acquire stationary strategy knowledge and an online interaction layer that employs a multi-agent reinforcement learning technology and the strategy knowledge that can be revised dynamically to interact with the environment. An agent with LMRL can improve its generalization capability, adaptability and coordination ability. Experiments show that the performance of LMRL can be better than those of a single agent reinforcement learning and Nash-Q. (c) 2006 Published by Elsevier Ltd.

Keyword:

reinforcement learning

multi-agent

layered model

A two-layered multi-agent reinforcement learning model and algorithm

摘要

AI总结

期刊

机构

引用论文