Tuning of Fuzzy Rules with a Real-coded Genetic Algorithm in Car Racing Game
Tuning of Fuzzy Rules with a Real-coded Genetic Algorithm in Car Racing Game
复制标题
赛车游戏中用实数编码遗传算法调整模糊规则
DOI：
10.1109/ifsa-scis.2017.8023267
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Noriyuki Fujimoto
中科院分区：
文献类型：
--
作者：
Akifumi Ise;Motohide Umano;Noriyuki Fujimoto
Car Racing Game是IEEE CEC 2007中的一个计算机程序竞赛，两个汽车智能体在二维平面上相互竞争以获取路点。智能体可以获得关于自身、其他智能体以及当前和下一个路点的信息。在我们以前的研究中，我们已经评估代理状态的当前和下一个路点与模糊规则，从他们的速度和距离和角度的路点，以决定采取哪一个路点。然后用模糊规则计算了转向和车速。然而，我们在比赛中没有赢得一些节目。在本文中，我们调整模糊规则的实数编码的遗传算法。用实数编码的遗传算法调优一个最好的方案的汽车代理可以赢得几乎所有的方案。此外，它得到更高的性能比普通的简单遗传算法。
Car Racing Game is a competition of computer programs in IEEE CEC 2007, where two car agents compete with each other for taking way points in a two-dimensional plane. The agent can get information on itself, the other agent, and the current and next way points. In our previous research, we have evaluated agent states for the current and next way points with fuzzy rules from their speeds and the distances and angles to way points, to decide which way point to take. Then we have calculated the steering and the speed with fuzzy rules. We, however, have not won some programs in the competition. In this paper, we tune fuzzy rules with a real-coded genetic algorithm. The car agent tuned with a real-coded genetic algorithm for one of the best programs can win almost all programs. Moreover, it gets higher in performance than an ordinary simple genetic algorithm.