Ammanabrolu Prithviraj, Riedl Mark O
School of Interactive Computing, Georgia Institute of Technology, 756 W Peachtree St NW, Atlanta, GA, USA.
Patterns (N Y). 2021 Sep 10;2(9):100316. doi: 10.1016/j.patter.2021.100316.
This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize that two key components in creating such agents are interactivity and environment grounding, shown to be vital parts of language learning in humans, and posit that interactive narratives should be the environments of choice for such training these agents. These games are simulations in which an agent interacts with the world through natural language-perceiving, acting upon, and talking to the world using textual descriptions, commands, and dialogue-and, as such, exist at the intersection of natural language processing, storytelling, and sequential decision making. We discuss the unique challenges a text games' puzzle-like structure combined with natural language state-and-action spaces provides: knowledge representation, common-sense reasoning, and exploration. Beyond the challenges described so far, progress in the realm of interactive narratives can be applied in adjacent problem domains. These applications provide interesting challenges of their own as well as extensions to those discussed so far. We describe three of them in detail: (1) evaluating artificial intelligence (AI) systems' common-sense understanding by automatically creating interactive narratives; (2) adapting abstract text-based policies to include other modalities, such as vision; and (3) enabling multi-agent and human-AI collaboration in shared, situated worlds.
本文提供了一个路线图，探讨如何赋予学习智能体理解和生成与上下文相关的自然语言的能力，以实现某个目标。我们假设，创建此类智能体的两个关键要素是交互性和环境基础，这两者已被证明是人类语言学习的重要组成部分，并认为交互式叙事应该是训练这些智能体的首选环境。这些游戏是模拟程序，其中智能体通过自然语言与世界进行交互——通过文本描述、命令和对话来感知世界、对世界采取行动并与世界交谈——因此，它们存在于自然语言处理、讲故事和序列决策的交叉点上。我们讨论了文本游戏类似谜题的结构与自然语言状态和动作空间相结合所带来的独特挑战：知识表示、常识推理和探索。除了上述挑战之外，交互式叙事领域的进展可以应用于相邻的问题领域。这些应用本身带来了有趣的挑战，也是对上述讨论的扩展。我们详细描述其中三个：（1）通过自动创建交互式叙事来评估人工智能（AI）系统的常识理解；（2）使基于抽象文本的策略能够纳入其他模态，如视觉；（3）在共享的情境化世界中实现多智能体和人机协作。
