Deep learning for procedural content generation
Procedural content generation in video games has a long history. Existing procedural
content generation methods, such as search-based, solver-based, rule-based and grammar …
content generation methods, such as search-based, solver-based, rule-based and grammar …
Search-based procedural content generation: A taxonomy and survey
The focus of this survey is on research in applying evolutionary and other metaheuristic
search algorithms to automatically generating content for games, both digital and nondigital …
search algorithms to automatically generating content for games, both digital and nondigital …
[图书][B] Artificial intelligence and games
GN Yannakakis, J Togelius - 2018 - Springer
Georgios N. Yannakakis Julian Togelius Page 1 Artificial Intelligence and Games Georgios N.
Yannakakis Julian Togelius Page 2 Artificial Intelligence and Games Page 3 Georgios N …
Yannakakis Julian Togelius Page 2 Artificial Intelligence and Games Page 3 Georgios N …
Evolving mario levels in the latent space of a deep convolutional generative adversarial network
Generative Adversarial Networks (GANs) are a machine learning approach capable of
generating novel example outputs across a space of provided training examples. Procedural …
generating novel example outputs across a space of provided training examples. Procedural …
A panorama of artificial and computational intelligence in games
GN Yannakakis, J Togelius - IEEE Transactions on …, 2014 - ieeexplore.ieee.org
This paper attempts to give a high-level overview of the field of artificial and computational
intelligence (AI/CI) in games, with particular reference to how the different core research …
intelligence (AI/CI) in games, with particular reference to how the different core research …
Super mario as a string: Platformer level generation via lstms
A Summerville, M Mateas - arXiv preprint arXiv:1603.00930, 2016 - arxiv.org
The procedural generation of video game levels has existed for at least 30 years, but only
recently have machine learning approaches been used to generate levels without specifying …
recently have machine learning approaches been used to generate levels without specifying …
The mario ai benchmark and competitions
S Karakovskiy, J Togelius - IEEE Transactions on …, 2012 - ieeexplore.ieee.org
This paper describes the Mario AI benchmark, a game-based benchmark for reinforcement
learning algorithms and game AI techniques developed by the authors. The benchmark is …
learning algorithms and game AI techniques developed by the authors. The benchmark is …
Procedural content generation: Goals, challenges and actionable steps
J Togelius, AJ Champandard, PL Lanzi, M Mateas… - 2013 - drops.dagstuhl.de
This chapter discusses the challenges and opportunities of procedural content generation
(PCG) in games. It starts with defining three grand goals of PCG, namely multi-level …
(PCG) in games. It starts with defining three grand goals of PCG, namely multi-level …
Experience-driven PCG via reinforcement learning: A Super Mario Bros study
We introduce a procedural content generation (PCG) framework at the intersections of
experience-driven PCG and PCG via reinforcement learning, named ED (PCG) RL, EDRL in …
experience-driven PCG and PCG via reinforcement learning, named ED (PCG) RL, EDRL in …
General video game level generation
This paper presents a framework and an initial study in general video game level
generation, the problem of generating levels for not only a single game but for any game …
generation, the problem of generating levels for not only a single game but for any game …