TL;DR
This paper presents a multi-objective search approach using NSGA-II to generate constructive level generators within Marahel language, demonstrating effectiveness across multiple puzzle domains.
Contribution
It introduces a method to evolve level generators in Marahel using multi-objective optimization, focusing on efficiency and problem-specific performance.
Findings
Generators achieved good fitness scores on most functions
Dependence on initial state was observed in Zelda and Sokoban
Restricted Marahel representation improved generator efficiency
Abstract
This paper introduces a new system to design constructive level generators by searching the space of constructive level generators defined by Marahel language. We use NSGA-II, a multi-objective optimization algorithm, to search for generators for three different problems (Binary, Zelda, and Sokoban). We restrict the representation to a subset of Marahel language to push the evolution to find more efficient generators. The results show that the generated generators were able to achieve good performance on most of the fitness functions over these three problems. However, on Zelda and Sokoban, they tend to depend on the initial state than modifying the map.
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
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
