Based on soccer robot simulation as its research platform, this paper studies the learning of high level strategy of multi-agent adversarial system.
本文以足球仿真机器人系统为研究平台，研究多智能体对抗系统的高层策略学习问题。
Due to the theoretical limitation that it assumes that an environment is Markovian, traditional reinforcement learning algorithms cannot be applied directly to multi-agent system.
由于强化学习理论的限制，在多智能体系统中马尔科夫过程模型不再适用，因此不能把强化学习直接用于多智能体的协作学习问题。
MAXQ, a hierarchical reinforcement learning method for multi-agent system, is proposed in recent years.
MAXQ分层多智能体学习方法是近年来被提出的一种新方法。
The issue of cooperation learning for autonomous micro-mobile robot is the main problem of multi-agent robot system theory.
自主微小型移动机器人的协作学习研究是多智能体机器人系统理论的主要研究方向。
Conclusion the comprehensive intervention could develop multi-agent learning ability of ld children, so as to improve their academic condition. The intervening technique is worth extended application.
结论综合干预训练能提高学习困难儿童多元学习能力，从而改善学业状况，值得推广应用。
Multi-Agent technology achieves the personalized in ITS, and reinforcement learning algorithm makes teaching strategies with the intelligent.
多代理体技术实现了教学的个性化，强化学习算法使得教学策略具有智能化。
Tis paper presents two-layer reinforcement learning method for multi-agent cooperation.
提出了多智能体协作的两层强化学习方法。
Tis paper presents two-layer reinforcement learning method for multi-agent cooperation.
提出了多智能体协作的两层强化学习方法。
应用推荐