Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models

TL;DR

This paper introduces a method that uses large language models to automatically relabel agent trajectories with meaningful instructions, improving instruction-following policies in reinforcement learning without extensive human annotations.

Contribution

It presents a novel open-ended instruction relabeling approach leveraging LLMs to enhance training data and learn versatile instruction-following policies from sparse rewards.

Findings

Improved sample efficiency in the Craftax environment

Enhanced instruction coverage and policy performance

Effective reduction of reliance on human-labeled datasets

Abstract

Developing effective instruction-following policies in reinforcement learning remains challenging due to the reliance on extensive human-labeled instruction datasets and the difficulty of learning from sparse rewards. In this paper, we propose a novel approach that leverages the capabilities of large language models (LLMs) to automatically generate open-ended instructions retrospectively from previously collected agent trajectories. Our core idea is to employ LLMs to relabel unsuccessful trajectories by identifying meaningful subtasks the agent has implicitly accomplished, thereby enriching the agent's training data and substantially alleviating reliance on human annotations. Through this open-ended instruction relabeling, we efficiently learn a unified instruction-following policy capable of handling diverse tasks within a single policy. We empirically evaluate our proposed method in the challenging Craftax environment, demonstrating clear improvements in sample efficiency, instruction coverage, and overall policy performance compared to state-of-the-art baselines. Our results highlight the effectiveness of utilizing LLM-guided open-ended instruction relabeling to enhance instruction-following reinforcement learning.