arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1305.6568cs.LGcs.ROstat.ML
收藏

足球运球任务的强化学习

Reinforcement Learning for the Soccer Dribbling Task

University of Waterloo(滑铁卢大学);Federal University of Pernambuco(伯南布哥联邦大学)

Arthur Carvalho, Renato Oliveira

摘要:

我们提出了一个强化学习解决方案的\emph{soccer dribbling task},在这种情况下,一个足球代理人必须从一个区域的开始到结束保持控球,作为对手试图获得控球。当对手使用固定策略时,运球者在每个决策点学习采取的最佳行动。在定义有意义的变量来表示状态空间和高层次的宏动作,将领域知识,我们描述了我们的应用程序的强化学习算法\emph{Sarsa}与CMAC函数逼近。我们的实验表明,训练期后,运球是能够完成其任务对一个强大的对手约58%的时间。

英文摘要:

We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represent the state space, and high-level macro-actions to incorporate domain knowledge, we describe our application of the reinforcement learning algorithm \emph{Sarsa} with CMAC for function approximation. Our experiments show that, after the training period, the dribbler is able to accomplish its task against a strong adversary around 58% of the time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑