Scholarlink

In the previous chapter we used sequence-based Deep Neural Networks (both Recurrent and Transformer-based), but sequences are only one possible way for us to represent the content that we wish to generate. For some types of content (like levels that have one dimension that is much larger than the others), this representation makes sense as the player engages with content sequentially—but this is not the only way for us to represent content.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Grid-Based DNN PCGML

  • 章节

  • 发表日期：

    2025年

查看全文
  • Matthew Guzdial,
  • Sam Snodgrass,
  • Adam Summerville

摘要

In the previous chapter we used sequence-based Deep Neural Networks (both Recurrent and Transformer-based), but sequences are only one possible way for us to represent the content that we wish to generate. For some types of content (like levels that have one dimension that is much larger than the others), this representation makes sense as the player engages with content sequentially—but this is not the only way for us to represent content.