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
Posted Content
Generative Design in Minecraft: Chronicle Challenge
TL;DR: The Chronicle Challenge as mentioned in this paper is an optional addition to the Settlement Generation Challenge in Minecraft, which focuses on the generation of a narrative based on the history of a generated settlement, expressed in natural language.
Proceedings ArticleDOI
Primal-improv: Towards co-evolutionary musical improvisation
TL;DR: The results of a quantitative study show that the Primal-Improv system is able to generate more interesting arrangements than ANNs evolved without a specific objective by only introducing simple rules as fitness functions.
Posted Content
Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games
Philip Bontrager,Ahmed Khalifa,Damien Anderson,Matthew Stephenson,Christoph Salge,Julian Togelius +5 more
TL;DR: An initial typology of deceptions is proposed which could help to better understand pitfalls and failure modes of (deep) reinforcement learning.
Proceedings Article
Behavioral Evaluation of Hanabi Rainbow DQN Agents and Rule-Based Agents
TL;DR: A key finding is that while most agents only learn to play well with partners seen during training, one particular agent leads the Rainbow algorithm towards a much more general policy.
Posted Content
Mario Level Generation From Mechanics Using Scene Stitching
TL;DR: In this paper, a level generation method for Super Mario by stitching together pre-generated "scenes" that contain specific mechanics, using mechanic-sequences from agent playthroughs as input specifications, is presented.