Generating Interactive Worlds with Text

  • Angela Fan Facebook/LORIA
  • Jack Urbanek Facebook
  • Pratik Ringshia Facebook
  • Emily Dinan Facebook
  • Emma Qian Facebook
  • Siddharth Karamcheti Facebook
  • Shrimai Prabhumoye Facebook
  • Douwe Kiela Facebook
  • Tim Rocktaschel Facebook/UCL
  • Arthur Szlam Facebook
  • Jason Weston Facebook

Abstract

Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this work, we investigate a machine learning approach for world creation using content from the multi-player text adventure game environment LIGHT (Urbanek et al. 2019). We introduce neural network based models to compositionally arrange locations, characters, and objects into a coherent whole. In addition to creating worlds based on existing elements, our models can generate new game content. Humans can also leverage our models to interactively aid in worldbuilding. We show that the game environments created with our approach are cohesive, diverse, and preferred by human evaluators compared to other machine learning based world construction algorithms.

Published
2020-04-03
Section
AAAI Technical Track: Game Playing and Interactive Entertainment