Generating Interactive Worlds with Text

By Angela Fan, Jack Urbanek, Pratik Ringshia, Emily Dinan, Emma Qian, Siddharth Karamcheti, Shrimai Prabhumoye, Douwe Kiela, Tim Rocktaschel, Arthur Szlam and 1 more. 2019

30 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Control and Systems Engineering, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Sociology and Political Science

Citations in the corpus

Continual Learning in Task-Oriented Dialogue Systems (2020, background): “by training models on humans-machine conversations in a open-domain fantasy world game (Fan et al., 2020) the models progressively improve, as measured by automatic metrics and online engagement scores.”
Situated Dialogue Learning through Procedural Environment Generation (2021, methodology): “Our choice of model is influenced by Fan et al. (2019) who report stateof-the-art retrieval performance for locations in LIGHT using this model.”
Increasing generality in machine learning through procedural content generation (2019, background): “For example, Fan et al. [73] very recently showed that a neural network can learn from crowd-sourced elements such as descriptions of locations and characters to create multi-player text adventure games.”