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

arXiv:2309.16347v2 Announce Type: replace-cross
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 …

abstract algorithms arxiv cs.cl cs.lg cs.ro current environments exploration framework horizon intrinsic language language models large language large language models llms manipulation reinforcement reinforcement learning robotic robotic manipulation struggle tasks type work