D
Diego Perez-Liebana
Researcher at Queen Mary University of London
Publications - 104
Citations - 2116
Diego Perez-Liebana is an academic researcher from Queen Mary University of London. The author has contributed to research in topics: Video game & General video game playing. The author has an hindex of 23, co-authored 93 publications receiving 1758 citations. Previous affiliations of Diego Perez-Liebana include University of Essex & Microsoft.
Papers
More filters
Journal ArticleDOI
The 2014 General Video Game Playing Competition
Diego Perez-Liebana,Spyridon Samothrakis,Julian Togelius,Tom Schaul,Simon M. Lucas,Adrien Couëtoux,Jerry Lee,Chong-U Lim,Tommy Thompson +8 more
TL;DR: All controllers submitted to the first General Video Game Playing Competition are described, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest.
Proceedings Article
General Video Game AI: competition, challenges, and opportunities
TL;DR: This short paper summarizes the motivation, infrastructure, results and future plans of General Video Game AI, stressing the findings and first conclusions drawn after two editions of the competition, and outlining the future plans.
Journal ArticleDOI
General Video Game AI: A Multitrack Framework for Evaluating Agents, Games, and Content Generation Algorithms
TL;DR: This survey paper presents the VGDL, the GVGAI framework, existing tracks, and reviews the wide use of GVgaI framework in research, education, and competitions five years after its birth.
Proceedings ArticleDOI
General Video Game Level Generation
TL;DR: The framework presented here builds on theGVG-AI and the Video Game Description Language in order to reap synergies from research activities connected to the General Video Game Playing Competition and will also form the basis for a new track of this competition.
Proceedings ArticleDOI
Deep Reinforcement Learning for General Video Game AI
TL;DR: In this article, the authors describe how they interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems, and characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of games written in a domain specific description language.