In real-world scenarios, it is desirable for embodied agents to have the ability to leverage human language to gain explicit or implicit knowledge for learning tasks. Despite recent progress, most previous approaches adopt simple low-level instructions as language inputs, which may not reflect natural human communication. It's not clear how to incorporate rich language use to facilitate task learning. To address this question, this paper studies different types of language inputs in facilitating reinforcement learning (RL) embodied agents. More specifically, we examine how different levels of language informativeness (i.e., feedback on past behaviors and future guidance) and diversity (i.e., variation of language expressions) impact agent learning and inference. Our empirical results based on four RL benchmarks demonstrate that agents trained with diverse and informative language feedback can achieve enhanced generalization and fast adaptation to new tasks. These findings highlight the pivotal role of language use in teaching embodied agents new tasks in an open world. Project website: https://github.com/sled-group/Teachable_RL

翻译：在现实场景中，我们希望具身智能体能够利用人类语言获取显性或隐性知识以完成学习任务。尽管近期取得进展，但大多数先前方法采用简单的低级指令作为语言输入，这可能无法反映自然的人类交流。如何融入丰富的语言使用以促进任务学习尚不明确。针对这一问题，本文研究了不同类型语言输入对促进强化学习具身智能体的作用。具体而言，我们考察了不同层次的语言信息量（即对过去行为的反馈与未来指导）和多样性（即语言表达的变化）如何影响智能体的学习与推理。基于四个强化学习基准的实验结果表明，通过多样且信息丰富的语言反馈训练的智能体能够实现更强的泛化能力以及对新任务的快速适应。这些发现凸显了语言使用在开放世界中教授具身智能体新任务的关键作用。项目网站：https://github.com/sled-group/Teachable_RL