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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xi, Jiajun, He, Yinong, Yang, Jianing, Dai, Yinpei, Chai, Joyce
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912098561294336
author Xi, Jiajun
He, Yinong
Yang, Jianing
Dai, Yinpei
Chai, Joyce
author_facet Xi, Jiajun
He, Yinong
Yang, Jianing
Dai, Yinpei
Chai, Joyce
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2410_24218
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
Xi, Jiajun
He, Yinong
Yang, Jianing
Dai, Yinpei
Chai, Joyce
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Robotics
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
title Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2410.24218