Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks

Eleftherios Triantafyllidis, Filippos Christianos, Alex Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Current reinforcement learning algorithms struggle in sparse and complex environments, most notably in long-horizon manipulation tasks entailing a plethora of different sequences. In this work, we propose the Intrinsically Guided Exploration from Large Language Models (IGE-LLMs) framework. By leveraging LLMs as an assistive intrinsic reward, IGE-LLMs guides the exploratory process in reinforcement learning to address intricate long-horizon with sparse rewards robotic manipulation tasks. We evaluate our framework and related intrinsic learning methods in an environment challenged with exploration, and a complex robotic manipulation task challenged by both exploration and long-horizons. Results show IGE-LLMs (i) exhibit notably higher performance over related intrinsic methods and the direct use of LLMs in decision-making, (ii) can be combined and complement existing learning methods highlighting its modularity, (iii) are fairly insensitive to different intrinsic scaling parameters, and (iv) maintain robustness against increased levels of uncertainty and horizons.
Original languageEnglish
Title of host publicationInternational Conference on Robotics and Automation (ICRA, 2024)
Place of PublicationYokohama, Japan
Number of pages10
Publication statusAccepted/In press - 29 Jan 2024
Event2024 IEEE International Conference on Robotics and Automation - Yokohama, Japan
Duration: 13 May 202417 May 2024


Conference2024 IEEE International Conference on Robotics and Automation
Abbreviated titleICRA 2024
Internet address

Keywords / Materials (for Non-textual outputs)

  • robot learning
  • machine Learning
  • robotics
  • manipulation
  • large language models
  • reinforcement learning
  • hierarchical learning


Dive into the research topics of 'Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks'. Together they form a unique fingerprint.

Cite this