2021/01/19 by Kirby Steckel, Steckel, Kirby, Jacob Schrum +1 · 1 citation
Computer Science · Economics, Econometrics and Finance · Engineering · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #FOS: Computer and information sciences #Human Motion and Animation #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Sports Analytics and Performance #cs.AI #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.2101.07868
arxiv created 2021/01/19 · openalex publication_date 2021/01/19 · arxiv updated 2021/01/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Generative Adversarial Networks (GANs) are capable of generating convincing imitations of elements from a training set, but the distribution of elements in the training set affects to difficulty of properly training the GAN and the quality of the outputs it produces. This paper looks at six different GANs trained on different subsets of data from the game Lode Runner. The quality diversity algorithm MAP-Elites was used to explore the set of quality levels that could be produced by each GAN, where quality was defined as being beatable and having the longest solution path possible. Interestingly, a GAN trained on only 20 levels generated the largest set of diverse beatable levels while a GAN trained on 150 levels generated the smallest set of diverse beatable levels, thus challenging the notion that more is always better when training GANs.