Interactive Fiction games are text-based simulations in which an agent
interacts with the world purely through natural language. They are ideal
environments for studying how to extend reinforcement learning agents to meet
the challenges of natural language understanding, partial observability, and
action generation in combinatorially-large text-based action spaces. We present
KG-A2C, an agent that builds a dynamic knowledge graph while exploring and
generates actions using a template-based action space. We contend that the dual
uses of the knowledge graph to reason about game state and to constrain natural
language generation are the keys to scalable exploration of combinatorially
large natural language actions. Results across a wide variety of IF games show
that KG-A2C outperforms current IF agents despite the exponential increase in
action space size.

本文介绍了 KG-A2C 代理，它通过构建动态知识图谱并使用基于模板的行动空间来生成动作，解决了在大规模组合自然语言行动空间中扩展强化学习代理以应对自然语言理解、部分可观察性和行动生成挑战的问题；从广泛的 IF 游戏结果来看，KG-A2C 优于当前的 IF 代理，尽管行动空间尺寸呈指数级增长。