However, collections of latent vectors can also be evolved directly, producing more chaotic levels.
Optimisation algorithms are commonly compared on benchmarks to get insight into performance differences.
no code implementations • 7 Jul 2020 • Thomas Bartz-Beielstein, Carola Doerr, Daan van den Berg, Jakob Bossek, Sowmya Chandrasekaran, Tome Eftimov, Andreas Fischbach, Pascal Kerschke, William La Cava, Manuel Lopez-Ibanez, Katherine M. Malan, Jason H. Moore, Boris Naujoks, Patryk Orzechowski, Vanessa Volz, Markus Wagner, Thomas Weise
This survey compiles ideas and recommendations from more than a dozen researchers with different backgrounds and from different institutes around the world.
While games have been used extensively as milestones to evaluate game-playing AI, there exists no standardised framework for reporting the obtained observations.
Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically.
This work aims to identify properties of real-world problems through a questionnaire on real-world single-, multi-, and many-objective optimization problems.
In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole, which would be useful in many areas, such as the generation of video game levels.
A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels.
This paper examines learning approaches for forward models based on local cell transition functions.
This paper provides a detailed investigation of using the Kullback-Leibler (KL) Divergence as a way to compare and analyse game-levels, and hence to use the measure as the objective function of an evolutionary algorithm to evolve new levels.
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent.
This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation.
This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.
In this paper, we propose a novel approach (SAPEO) to support the survival selection process in multi-objective evolutionary algorithms with surrogate models - it dynamically chooses individuals to evaluate exactly based on the model uncertainty and the distinctness of the population.
In this paper, the feasibility of automatic balancing using simulation- and deck-based objectives is investigated for the card game top trumps.