摘要
针对多机器人协作学习时出现的学习速度慢、学习效率低等问题,提出了一种基于π演算心智模型的足球机器人协作Q学习方法,描述了机器人的运动模型,定义了球场现状、目标、意图、行为、协作、请求、扩展知识、能力判断和联合意图等机器人心智状态,构造了联合奖励函数。最后通过实验验证了方法的有效性。
Concerning the low speed and low efficiency of learning in robot soccer when cooperating between muhirobots, a cooperative Q learning method based on the mental model of π calculus was proposed, in which the mental states were defined as the field state, goal, intention, action, cooperation, request, expanding knowledge, capability judging and connected intention, etc, and the combinational reward function was constructed. The validity of method was verified through experiments.
出处
《计算机应用》
CSCD
北大核心
2011年第3期654-656,669,共4页
journal of Computer Applications
基金
广东高校优秀青年创新人才培育项目(201180)
国家863计划项目(2007AA041603
2006AA040202)
国家自然科学基金资助项目(60905047
61075076
61075077)
国家重点实验室项目(SKLRS200902C)
广东省自然科学基金资助项目(8152500002000003)
关键词
多机器人
协作
Q学习
心智状态
multi-robot
cooperation
Q learning
mental state
