Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks
This addresses a critical bottleneck in reinforcement learning for robotics, offering a modular solution to improve exploration in sparse-reward environments, though it appears incremental as it builds on existing intrinsic learning methods.
The paper tackled the problem of sparse and complex long-horizon robotic manipulation tasks by proposing the IGE-LLMs framework, which uses large language models as an intrinsic reward to guide exploration in reinforcement learning, resulting in notably higher performance over related methods and robustness against uncertainty.
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.