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
Searching for good and diverse game levels
TL;DR: This work investigates several search-based approaches to creating good and diverse game content, in particular approaches based on evolution strategies with or without diversity preservation mechanisms, novelty search and random search.
Journal ArticleDOI
Affective evolutionary music composition with MetaCompose
TL;DR: The results of these studies demonstrate that each part of the generation system improves the perceived quality of the music produced, and how valence expression via dissonance produces the perceived affective state.
Book ChapterDOI
Arms races and car races
Julian Togelius,Simon M. Lucas +1 more
TL;DR: A sensor representation is devised, and various methods of evolving car controllers for competitive racing are explored, and a tendency to specialization and the reactive nature of the controller architecture are found to limit evolutionary progress.
Proceedings ArticleDOI
Investigating MCTS modifications in general video game playing
TL;DR: The results of the experiments show that a combination of two MCTS modifications can improve the performance of the vanilla M CTS controller, but the effectiveness of the modifications highly depends on the particular game being played.
Posted Content
Procedural Level Generation Improves Generality of Deep Reinforcement Learning
Niels Justesen,Ruben Rodriguez Torrado,Philip Bontrager,Ahmed Khalifa,Julian Togelius,Sebastian Risi +5 more
TL;DR: This paper presents an approach to prevent overfitting by generating more general agent controllers, through training the agent on a completely new and procedurally generated level each episode.