Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
This work addresses the challenge of teaching embodied agents in real-world scenarios using more natural human-like language, representing an incremental improvement over previous methods that relied on simple low-level instructions.
The paper tackled the problem of how to incorporate rich, natural language inputs to improve reinforcement learning for embodied agents, finding that diverse and informative language feedback enhances generalization and fast adaptation across four RL benchmarks.
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