J
Julian Togelius
Researcher at New York University
Publications - 442
Citations - 15850
Julian Togelius is an academic researcher from New York University. The author has contributed to research in topics: Game design & Game mechanics. The author has an hindex of 58, co-authored 420 publications receiving 13135 citations. Previous affiliations of Julian Togelius include Dalle Molle Institute for Artificial Intelligence Research & Harvard University.
Papers
More filters
Proceedings ArticleDOI
Monte Mario: platforming with MCTS
TL;DR: When adding noise to the benchmark, MCTS outperforms the best known algorithm for these levels, and a combination of these modifications is found to lead to almost perfect play on linear levels.
Proceedings ArticleDOI
Procedural Content Generation through Quality Diversity
TL;DR: In the last few years, a handful of applications of QD to procedural content generation and game playing have been proposed; this work discusses these and proposes challenges for future work.
Journal ArticleDOI
Controllable procedural map generation via multiobjective evolution
Julian Togelius,Mike Preuss,Nicola Beume,Simon Wessing,Johan Hagelbäck,Georgios N. Yannakakis,Corrado Grappiolo +6 more
TL;DR: This paper designs two different evolvable map representations, one for an imaginary generic strategy game based on heightmaps, and one for the classic RTS game StarCraft, showing how multiobjective evolutionary algorithms can be used to procedurally generate complete and playable maps for real-time strategy (RTS) games.
Proceedings ArticleDOI
A procedural procedural level generator generator
TL;DR: This paper presents a procedural procedural level generator generator for Super Mario Bros. that is an interactive evolutionary algorithm that evolves agent-based level generators.
Posted Content
Autoencoder-augmented Neuroevolution for Visual Doom Playing
Samuel Alvernaz,Julian Togelius +1 more
TL;DR: In this paper, the authors train an autoencoder to create a comparatively low-dimensional representation of the environment observation, and then use CMA-ES to train neural network controllers acting on this input data.