使用多个生成对抗网络为Mega Man构建更好的连接级别
Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man
摘要:
生成对抗网络(GANs)可以为各种游戏生成关卡。这篇论文的重点是将GAN生成的段以蛇形模式组合起来,为Mega Man创建关卡。这些关卡中的相邻段可以在任何方向上正交相邻,这意味着一个精细的段可能会在其相邻段之间施加障碍,这取决于训练集中哪种类型的段被最接近地模拟:水平段、垂直段或角段。为了选择适当的段,在不同类型的段上训练多个GANs,以确保段之间更好的流动。通过进化层次中连接的段的潜在向量,进一步改进了流程,以最大化层次的解决方案路径的长度。使用多个GANs来表示不同类型的段,与使用一个GAN来表示所有段类型相比,其解决方案路径明显更长,并且人体研究验证了这些层次比一个GAN产生的层次更有趣,并且具有更人性化的设计。
英文摘要:
Generative Adversarial Networks (GANs) can generate levels for a variety of games. This paper focuses on combining GAN-generated segments in a snaking pattern to create levels for Mega Man. Adjacent segments in such levels can be orthogonally adjacent in any direction, meaning that an otherwise fine segment might impose a barrier between its neighbor depending on what sorts of segments in the training set are being most closely emulated: horizontal, vertical, or corner segments. To pick appropriate segments, multiple GANs were trained on different types of segments to ensure better flow between segments. Flow was further improved by evolving the latent vectors for the segments being joined in the level to maximize the length of the level's solution path. Using multiple GANs to represent different types of segments results in significantly longer solution paths than using one GAN for all segment types, and a human subject study verifies that these levels are more fun and have more human-like design than levels produced by one GAN.
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。