论文标题
图表限制了自然语言动作空间的强化学习
Graph Constrained Reinforcement Learning for Natural Language Action Spaces
论文作者
论文摘要
互动小说游戏是基于文本的模拟，其中代理商纯粹通过自然语言与世界互动。它们是研究如何扩展强化学习者的理想环境，以应对基于文本的作用空间中自然语言理解，部分观察性和动作产生的挑战。我们提出KG-A2C，该代理在探索和使用基于模板的动作空间探索和生成动作的同时构建动态知识图。我们认为，知识图的双重用途来推理游戏状态并限制自然语言的生成是对组合上大型自然语言动作的可扩展探索的关键。在各种游戏中的结果表明，尽管动作空间大小的指数增加，但如果代理，则KG-A2C的表现要优于当前。
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.
