Toward Automated Quest Generation in Text-Adventure Games

By Prithviraj Ammanabrolu, William Broniec, Alex Mueller, Jeremy Paul, Mark O. Riedl. 2019

32 citations recorded by the source corpus.

Interactive fictions, or text-adventures, are games in which a player interacts with a world entirely through textual descriptions and text actions. Text-adventure games are typically structured as puzzles or quests wherein the player must execute certain actions in a certain order to succeed. In this paper, we consider the problem of procedurally generating a quest, defined as a series of actions required to progress towards a goal, in a text-adventure game. Quest generation in text environments is challenging because they must be semantically coherent. We present and evaluate two quest generation techniques: (1) a Markov model, and (2) a neural generative model. We specifically look at generating quests about cooking and train our models on recipe data. We evaluate our techniques with human participant studies looking at perceived creativity and coherence.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Sociology and Political Science, Natural Language Processing

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 Developmental and Educational Psychology

In Sociology and Political Science

In Natural Language Processing

Citations in the corpus

Keep CALM and Explore: Language Models for Action Generation in Text-based Games (2020, methodology): “Ammanabrolu et al. (2019) used Markov chains and neural language models to procedurally generate quests for TextWorld-like games.”
Graph Constrained Reinforcement Learning for Natural Language Action Spaces (2020, background): “Ammanabrolu et al. (2019) explore procedural content generation in text-adventure games—looking at constructing a quest for a given game world, and use knowledge graphs to ground generative systems trained to produce quest content.”
Situated Dialogue Learning through Procedural Environment Generation (2021, background): “…representation (Ammanabrolu and Riedl, 2019; Adhikari et al., 2020; Sautier et al., 2020), combinatorial state-action spaces (Ammanabrolu and Hausknecht, 2020; Ammanabrolu et al., 2020c), and commonsense reasoning (Ammanabrolu and Riedl, 2019; Murugesan et al., 2020, 2021; Dambekodi et al., 2020).”