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

TL;DR

This paper introduces IGE-LLMs, a framework that uses large language models as intrinsic rewards to improve exploration in reinforcement learning for complex, long-horizon robotic manipulation tasks with sparse rewards.

Contribution

The paper presents a novel method leveraging LLMs as intrinsic rewards to enhance exploration in long-horizon robotic tasks, demonstrating improved performance and robustness.

Findings

IGE-LLMs outperform related intrinsic methods and direct LLM decision-making.

IGE-LLMs are modular and can complement existing learning methods.

IGE-LLMs are robust to parameter variations and increased uncertainty.

Abstract

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.