Quality-diversity in dissimilarity spaces
arXiv:2211.12337v32 citationsh-index: 7
Originality Synthesis-oriented
AI Analysis
This work addresses diversity optimization in machine learning, but appears incremental as it extends existing methods to new mathematical frameworks.
The paper tackled the problem of quantifying and maximizing diversity in quality-diversity algorithms by applying magnitude theory to dissimilarity spaces, resulting in a general version of Go-Explore with promising performance.
The theory of magnitude provides a mathematical framework for quantifying and maximizing diversity. We apply this framework to formulate quality-diversity algorithms in generic dissimilarity spaces. In particular, we instantiate and demonstrate a very general version of Go-Explore with promising performance.