Interactive Reinforcement Learning from Natural Language Feedback

TARAKLI, Imene, VINANZI, Samuele and DI NUOVO, Alessandro (2024). Interactive Reinforcement Learning from Natural Language Feedback. In: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 11478-11484. [Book Section]

Documents
34492:736967
[thumbnail of IROS (9).pdf]
Preview
PDF
IROS (9).pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (471kB) | Preview
Abstract
Large Language Models (LLMs) are increasingly influential in advancing robotics. This paper introduces ECLAIR (Evaluative Corrective Guidance Language as Reinforcement), a novel framework that leverages LLMs to interpret and incorporate diverse natural language feedback into robotic learning. ECLAIR unifies various forms of human advice into actionable insights within a Reinforcement Learning context, enabling more efficient robot instruction. Experiments with real-world users demonstrate that ECLAIR accelerates the robot’s learning process, aligning its policy closer to optimal from the outset and reducing the need for extensive human intervention. Additionally, ECLAIR effectively integrates multiple types of advice and adapts well to prompt modifications. It also supports multilingual instruction, broadening its applicability and fostering more inclusive human-robot interactions. Project website: https://sites.google.com/view/eclairiros
More Information
Statistics

Downloads

Downloads per month over past year

Loading...Loading...

View more statistics

Share
Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email

Actions (login required)

View Item View Item