# LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning

## TL;DR

This paper introduces LLMDPD, a novel offline reinforcement learning approach that uses large language models and trajectory prompts to improve generalization to new tasks, outperforming existing methods.

## Contribution

The paper proposes a new method combining language and trajectory prompts with diffusion models to enhance offline RL generalization to unseen tasks.

## Key findings

- LLMDPD outperforms state-of-the-art offline RL methods on unseen tasks.
- Using language and trajectory prompts improves policy generalization.
- The approach effectively leverages LLMs for task understanding in RL.

## Abstract

Reinforcement Learning (RL) is known for its strong decision-making capabilities and has been widely applied in various real-world scenarios. However, with the increasing availability of offline datasets and the lack of well-designed online environments from human experts, the challenge of generalization in offline RL has become more prominent. Due to the limitations of offline data, RL agents trained solely on collected experiences often struggle to generalize to new tasks or environments. To address this challenge, we propose LLM-Driven Policy Diffusion (LLMDPD), a novel approach that enhances generalization in offline RL using task-specific prompts. Our method incorporates both text-based task descriptions and trajectory prompts to guide policy learning. We leverage a large language model (LLM) to process text-based prompts, utilizing its natural language understanding and extensive knowledge base to provide rich task-relevant context. Simultaneously, we encode trajectory prompts using a transformer model, capturing structured behavioral patterns within the underlying transition dynamics. These prompts serve as conditional inputs to a context-aware policy-level diffusion model, enabling the RL agent to generalize effectively to unseen tasks. Our experimental results demonstrate that LLMDPD outperforms state-of-the-art offline RL methods on unseen tasks, highlighting its effectiveness in improving generalization and adaptability in diverse settings.