论文标题
具有常识性知识的基于文本的RL代理：新的挑战，环境和基线
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
论文作者
论文摘要
基于文本的游戏已成为强化学习（RL）研究的重要测试床，要求RL代理将基础语言理解与顺序决策相结合。在本文中，我们研究了将RL代理注入常识性知识的问题。这种知识将使代理人通过修剪难以置信的行动，并执行外观计划来确定当前行动如何影响未来的世界国家，从而有效地在世界范围内采取行动。我们设计了一个新的基于文本的游戏环境，称为TextWorld Commonsense（TWC），用于培训和评估RL代理，并具有有关对象，其属性和负担能力的特定常识性知识。我们还介绍了几种基线RL代理，它们跟踪顺序上下文并动态地检索概念网的相关常识知识。我们表明，在TWC中纳入常识性知识的代理商的表现更好，同时更有效地行动。我们进行用户研究以估计TWC上的人类绩效，并表明将来有足够的改进空间。
Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of infusing RL agents with commonsense knowledge. Such knowledge would allow agents to efficiently act in the world by pruning out implausible actions, and to perform look-ahead planning to determine how current actions might affect future world states. We design a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances. We also introduce several baseline RL agents which track the sequential context and dynamically retrieve the relevant commonsense knowledge from ConceptNet. We show that agents which incorporate commonsense knowledge in TWC perform better, while acting more efficiently. We conduct user-studies to estimate human performance on TWC and show that there is ample room for future improvement.
