Toward Automated Quest Generation in Text-Adventure Games
This addresses the challenge of creating semantically coherent quests for text-adventure game developers, but it is incremental as it builds on existing generation techniques.
The paper tackled the problem of procedurally generating quests in text-adventure games, focusing on cooking quests trained on recipe data, and found that neural generative models outperformed Markov models in human evaluations of creativity and coherence.
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.