滚动地平线NEAT适用于一般视频游戏
Rolling Horizon NEAT for General Video Game Playing
摘要：
本文提出了一种新的统计前向规划（SFP）方法--滚动时域神经网络拓扑进化（rhNEAT）。与传统的滚动地平线进化不同，其中进化算法负责进化一系列动作，rhNEAT实时进化神经网络的权重和连接，在返回一个动作以在游戏中执行之前提前规划几个步骤。在20个GVGAI游戏的集合中探索了不同版本的算法，并与其他SFP方法和最先进的结果进行了比较。尽管结果总体上并不比其他SFP方法更好，但rhNEAT适应不断变化的游戏特征的性质允许在传统上其他方法难以实现的游戏中建立新的最新记录。这里提出的算法是通用的，并介绍了一种新的方式来表示滚动时域进化技术内的信息。
英文摘要：
This paper presents a new Statistical Forward Planning (SFP) method, Rolling Horizon NeuroEvolution of Augmenting Topologies (rhNEAT). Unlike traditional Rolling Horizon Evolution, where an evolutionary algorithm is in charge of evolving a sequence of actions, rhNEAT evolves weights and connections of a neural network in real-time, planning several steps ahead before returning an action to execute in the game. Different versions of the algorithm are explored in a collection of 20 GVGAI games, and compared with other SFP methods and state of the art results. Although results are overall not better than other SFP methods, the nature of rhNEAT to adapt to changing game features has allowed to establish new state of the art records in games that other methods have traditionally struggled with. The algorithm proposed here is general and introduces a new way of representing information within rolling horizon evolution techniques.
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。
