analiza aiqbench
This paper advances quality-diversity optimization by applying the theory of magnitude to generic dissimilarity spaces, offering a generalized framework for Go-Explore algorithms. The work contributes directly to machine learning research by providing mathematical rigor for maximizing solution diversity in complex search landscapes.
Quality-diversity in dissimilarity spaces
arXiv:2211.12337v4 Announce Type: replace Abstract: 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.
Abstract: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.
Patched Section 7 (not in the GECCO 2023 version at DOI https://doi.org/10.1145/3583131.3590409) with inline forward reference to https://arxiv.org/html/2509.19565 and this https URL, which contain the correct algorithm and proofs. No experimental results are materially affected in either this version or the GECCO one
Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Optimization and Control (math.OC)
arXiv:2211.12337 [cs.AI]
(or arXiv:2211.12337v4 [cs.AI] for this version)
https://doi.org/10.1145/3583131.3590409 DOI(s) linking to related resources
Text integral sub licența deschisă a publicației · 109 cuvinte
Subiecte conexe
Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning
arXiv · 16 sept. 2026
BRICS Draws a New Global Line: Full Text of New Delhi Declaration
slguardian.org · 12 sept. 2026
Autonomously Acquiring Robot Manipulation Skills with Language-Driven Quality-Diversity
arXiv · 2 sept. 2026
Generation of Diverse and Functional Robot Designs using Superquadrics Parametrisation and Quality-Diversity
arXiv · 10 iun. 2026