启发式多类神经元自动机的能级生成
Illuminating Diverse Neural Cellular Automata for Level Generation
摘要：
我们提出了一种方法，生成不同的神经元胞自动机（NCA）的集合来设计视频游戏的水平。虽然NCA到目前为止只通过监督学习进行训练，我们提出了一个质量多样性（QD）的方法来生成一个NCA级生成器的集合。通过将问题构建为QD问题，我们的方法可以训练不同级别的生成器，其输出级别根据美学或功能标准而变化。为了有效地生成NCA，我们通过协方差矩阵自适应MAP-Elites（CMA-ME）训练生成器，这是一种专门用于连续搜索空间的质量多样性算法。我们应用我们的新方法来生成几个2D瓷砖为基础的游戏水平生成器：迷宫游戏，推箱子，塞尔达。我们的研究结果表明，CMA-ME可以产生小的NCA是不同的，但有能力，往往满足复杂的可解性标准确定性代理。我们与经过训练以产生各种生成器集合的组合模式生成网络（CPPN）基线进行比较，并表明NCA表示可以更好地探索水平空间。
英文摘要：
We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels. While NCAs have so far only been trained via supervised learning, we present a quality diversity (QD) approach to generating a collection of NCA level generators. By framing the problem as a QD problem, our approach can train diverse level generators, whose output levels vary based on aesthetic or functional criteria. To efficiently generate NCAs, we train generators via Covariance Matrix Adaptation MAP-Elites (CMA-ME), a quality diversity algorithm which specializes in continuous search spaces. We apply our new method to generate level generators for several 2D tile-based games: a maze game, Sokoban, and Zelda. Our results show that CMA-ME can generate small NCAs that are diverse yet capable, often satisfying complex solvability criteria for deterministic agents. We compare against a Compositional Pattern-Producing Network (CPPN) baseline trained to produce diverse collections of generators and show that the NCA representation yields a better exploration of level-space.
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。
