Increasing generality in machine learning through procedural content generation
نویسندگان
چکیده
منابع مشابه
Procedural Content Generation via Machine Learning (PCGML)
Adam Summerville1, Sam Snodgrass2, Matthew Guzdial3, Christoffer Holmgård4, Amy K. Hoover5, Aaron Isaksen6, Andy Nealen6, and Julian Togelius6, 1Department of Computational Media, University of California, Santa Cruz, CA 95064, USA 2College of Computing and Informatics, Drexel University, Philadelpia, PA 19104, USA 3School of Electrical and Computer Engineering, Georgia Institute of Technology,...
متن کاملCombinatorial Creativity for Procedural Content Generation via Machine Learning
In this paper we propose the application of techniques from the field of creativity research to machine learned models within the domain of games. This application allows for the creation of new, distinct models without additional training data. The techniques in question are combinatorial creativity techniques, defined as techniques that combine two sets of input to create novel output sets. W...
متن کاملCreating Dreamlike Game Worlds Through Procedural Content Generation
This article describes the process of designing a point-andclick adventure game that aimed at using dream logic as the basis to create its narrative puzzles. The technical solution to tackle this challenge was using Procedural Content Generation (PCG) as the design approach, which was used expressively to recreate the instability and changeability of dreams. Although PCG brought about replayabi...
متن کاملPatterns and Procedural Content Generation
Procedural content generation and design patterns could potentially be combined in several different ways in game design. This paper discusses how to combine the two, using automatic platform game level design as an example. The paper also present work towards a pattern-based level generator for Super Mario Bros, namely an analysis of the levels of the original Super Mario Bros game into 23 dif...
متن کاملCognitively-Grounded Procedural Content Generation
Procedural content generators overly focused on numeric variations of content suffer from what we term the Kaleidoscope Effect: because we readily grasp the potential of the generative space, it is not interesting. In this position paper, we argue that the future of procedural content generation will be limited by this effect. We therefore propose a shift toward cognitively-grounded procedural ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Nature Machine Intelligence
سال: 2020
ISSN: 2522-5839
DOI: 10.1038/s42256-020-0208-z