In this work, we explore techniques for augmenting interactive agents with information from symbolic modules, much like humans use tools like calculators and GPS systems to assist with arithmetic and navigation. We test our agent's abilities in text games -- challenging benchmarks for evaluating the multi-step reasoning abilities of game agents in grounded, language-based environments. Our experimental study indicates that injecting the actions from these symbolic modules into the action space of a behavior cloned transformer agent increases performance on four text game benchmarks that test arithmetic, navigation, sorting, and common sense reasoning by an average of 22%, allowing an agent to reach the highest possible performance on unseen games. This action injection technique is easily extended to new agents, environments, and symbolic modules.

翻译：在这项工作中，我们探索了用符号模块的信息增强交互代理的技术，类似于人类使用计算器和GPS系统等工具辅助算术与导航。我们在文本游戏中测试代理的能力——这些游戏是评估游戏代理在基于语言的环境中多步推理能力的挑战性基准。我们的实验研究表明，将来自这些符号模块的动作注入到行为克隆Transformer代理的动作空间中，在四个分别测试算术、导航、排序和常识推理的文本游戏基准上，平均性能提升了22%，使得代理能在未见过的游戏中达到最高可能性能。这种动作注入技术易于扩展到新的代理、环境和符号模块。