Generating Interactive Worlds with Text
arXiv:1911.09194
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. 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.
References in corpus (10)
- Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
- Hierarchical Neural Story Generation
- Understanding the Origins of Bias in Word Embeddings
- TextWorld: A Learning Environment for Text-based Games
- StarSpace: Embed All The Things!
- Be Your Own Prada: Fashion Synthesis with Structural Coherence
- Gender Bias in Contextualized Word Embeddings
- What makes a good conversation? How controllable attributes affect human judgments
- Domain Authoring Assistant for Intelligent Virtual Agents
- GenerationMania: Learning to Semantically Choreograph