Illuminating search spaces by mapping elites
Jean-Baptiste Mouret, Jeff Clune

TL;DR
The paper introduces MAP-Elites, a novel algorithm that maps high-performing solutions across multiple dimensions, providing a comprehensive view of search spaces and yielding diverse, high-quality solutions in various domains.
Contribution
It presents MAP-Elites, a new algorithm that illuminates search spaces by mapping high-performing solutions across user-defined dimensions, enhancing understanding and diversity of solutions.
Findings
MAP-Elites produces diverse high-performing solutions.
It outperforms state-of-the-art algorithms in finding better overall solutions.
The algorithm is effective across multiple problem domains.
Abstract
Many fields use search algorithms, which automatically explore a search space to find high-performing solutions: chemists search through the space of molecules to discover new drugs; engineers search for stronger, cheaper, safer designs, scientists search for models that best explain data, etc. The goal of search algorithms has traditionally been to return the single highest-performing solution in a search space. Here we describe a new, fundamentally different type of algorithm that is more useful because it provides a holistic view of how high-performing solutions are distributed throughout a search space. It creates a map of high-performing solutions at each point in a space defined by dimensions of variation that a user gets to choose. This Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) algorithm illuminates search spaces, allowing researchers to understand how…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Wild breakthrough on Math after 56 years... [Exclusive]· youtube
Taxonomy
TopicsReinforcement Learning in Robotics · Digital Games and Media · Artificial Intelligence in Games
