顾冬雷, 陈卫东, 席裕庚. 机器人足球赛中基于增强学习的任务分工[J]. 机器人, 2000, 22(6): 482-489.
引用本文: 顾冬雷, 陈卫东, 席裕庚. 机器人足球赛中基于增强学习的任务分工[J]. 机器人, 2000, 22(6): 482-489.
GU Dong-lei, CHEN Wei-dong, XI Yu-geng. ROLE DIVERSITY IN ROBOT SOCCER BASED ON REINFORCEMENT LEARNING[J]. ROBOT, 2000, 22(6): 482-489.
Citation: GU Dong-lei, CHEN Wei-dong, XI Yu-geng. ROLE DIVERSITY IN ROBOT SOCCER BASED ON REINFORCEMENT LEARNING[J]. ROBOT, 2000, 22(6): 482-489.

机器人足球赛中基于增强学习的任务分工

ROLE DIVERSITY IN ROBOT SOCCER BASED ON REINFORCEMENT LEARNING

  • 摘要: 本文研究了机器人足球赛中利用增强学习进行角色分工的问题,通过仿真试验和理论分析,指出文1中采取无限作用范围衰减奖励优化模型(infinite-horizon discounted model)的Q学习算法对该任务不合适,并用平均奖励模型(average-reward model)对算法进行了改进,实验表明改进后学习的收敛速度以及系统的性能都提高了近一倍.

     

    Abstract: In this paper, the role diversity based on reinforcement learning in robot soccer is studied. Through simulation and analysis, it is shown that the Q algorithm infinite-horizon discounted model in is not suitable to this task. Instead of that, average-reward model is used for improving the algorithm. Simulation experiments show that the convergence rate in learning and the system performance are twice increased after improvement.

     

/

返回文章
返回