A Novel CNet-assisted Evolutionary Level Repairer and Its Applications to Super Mario Bros
This addresses the need for autonomous repair of game levels to reduce reliance on complex rule-based systems, but it is incremental as it builds on existing evolutionary and learning methods.
The authors tackled the problem of repairing defective game levels generated by latent variable evolution by proposing CNet, a model that learns tile probability distributions from real levels to detect illegal patterns, and an evolutionary repairer that searches for optimal replacements. In a case study on Super Mario Bros., the approach effectively repaired GAN-generated and artificially destroyed levels, though no concrete numbers were provided.
Applying latent variable evolution to game level design has become more and more popular as little human expert knowledge is required. However, defective levels with illegal patterns may be generated due to the violation of constraints for level design. A traditional way of repairing the defective levels is programming specific rule-based repairers to patch the flaw. However, programming these constraints is sometimes complex and not straightforward. An autonomous level repairer which is capable of learning the constraints is needed. In this paper, we propose a novel approach, CNet, to learn the probability distribution of tiles giving its surrounding tiles on a set of real levels, and then detect the illegal tiles in generated new levels. Then, an evolutionary repairer is designed to search for optimal replacement schemes equipped with a novel search space being constructed with the help of CNet and a novel heuristic function. The proposed approaches are proved to be effective in our case study of repairing GAN-generated and artificially destroyed levels of Super Mario Bros. game. Our CNet-assisted evolutionary repairer can also be easily applied to other games of which the levels can be represented by a matrix of objects or tiles.