Evaluation-function modeling with multi-layered perceptron for RoboCup soccer 2D simulation
Evaluation-function modeling with multi-layered perceptron for RoboCup soccer 2D simulation
复制标题
DOI：
10.1007/s10015-020-00602-w
复制
发表时间：
2020-04
影响因子：
0.9
通讯作者：
Takuya Fukushima;T. Nakashima;Hidehisa Akiyama
中科院分区：
文献类型：
--
作者：
Takuya Fukushima;T. Nakashima;Hidehisa Akiyama
在RoboCup足球模拟2D联赛中，球员在真实的时间内在每个循环中做出决定。一个球队的表现在很大程度上取决于智能体的决策过程，这是由一个行动规划方法和足球场的评价函数。在这项工作中，合作行动规划的基础上，树搜索。每个动作都由一个评价函数进行评价。我们采用多层感知器来构造一个评价函数。我们研究的足球代理的性能时，各种功能集被用作神经网络的输入。一个特征向量是由一个专家组从日志文件中提取的踢序列执行。为了研究我们的方法的效率，我们比较了一个团队的表现，使用神经网络建模的评价函数对一个团队使用手动调整的评价函数。
In the RoboCup soccer simulation 2D league, players make a decision at each cycle in real time. The performance of a team highly depends on the agents’ decision-making process, which is composed of a action planning method and an evaluation function of the soccer field. In this work, a cooperative action planning based on the tree search is employed. Each action is evaluated by an evaluation function. We employ a multi-layered perceptron to construct an evaluation function. We examine the performance of the soccer agents when various sets of features are used as the input of the neural network. A feature vector is made of kick sequences executed by an expert team extracted from log files. To investigate the efficiency of our approach, we compare the performance of a team using an evaluation function modeled by neural networks against a team using a hand-tuned evaluation function.