Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

Jiajun Xi, Yinong He, Jianing Yang, Yinpei Dai, Joyce Chai


Abstract
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. We expect human language to be informative (i.e., providing feedback on agents’ past behaviors and offering guidance on achieving their future goals) and diverse (i.e., encompassing a wide range of expressions and style nuances). To enable flexibility of language use in teaching agents tasks, 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 and diversity 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.
Anthology ID:
2024.emnlp-main.237
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4097–4114
Language:
URL:
https://aclanthology.org/2024.emnlp-main.237
DOI:
Bibkey:
Cite (ACL):
Jiajun Xi, Yinong He, Jianing Yang, Yinpei Dai, and Joyce Chai. 2024. Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4097–4114, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use (Xi et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.237.pdf
Software:
 2024.emnlp-main.237.software.zip