arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.06283cs.CLcs.AI
收藏

文本冒险游戏中任务的自动生成

Toward Automated Quest Generation in Text-Adventure Games

School of Interactive Computing(交互计算学院);Georgia Institute of Technology(佐治亚理工学院)

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

摘要:

交互式小说,或文本冒险,是玩家完全通过文本描述和文本动作与世界互动的游戏。文本冒险游戏通常被构造为谜题或任务,其中玩家必须以特定顺序执行特定动作才能成功。在本文中,我们考虑的问题,程序生成一个任务,定义为一系列的行动所需的进展朝着一个目标,在文本冒险游戏。文本环境中的任务生成具有挑战性,因为它们必须是语义连贯的。我们提出并评估了两种任务生成技术:(1)马尔可夫模型,(2)神经生成模型。我们特别关注生成关于烹饪的任务,并根据食谱数据训练我们的模型。我们评估我们的技术与人类参与者的研究看感知的创造力和连贯性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑