CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning

TL;DR

This paper introduces CO-RFT, a novel offline reinforcement learning method with action chunking for fine-tuning vision-language-action models, significantly improving robotic control success rates and generalization with limited demonstration data.

Contribution

We propose Chunked RL and CO-RFT, novel algorithms that enhance sample efficiency and stability in fine-tuning VLA models for robotic tasks using offline RL with action chunking.

Findings

57% success rate improvement over previous methods

22.3% reduction in cycle time

44.3% success rate in unseen positions

Abstract

Vision-Language-Action (VLA) models demonstrate significant potential for developing generalized policies in real-world robotic control. This progress inspires researchers to explore fine-tuning these models with Reinforcement Learning (RL). However, fine-tuning VLA models with RL still faces challenges related to sample efficiency, compatibility with action chunking, and training stability. To address these challenges, we explore the fine-tuning of VLA models through offline reinforcement learning incorporating action chunking. In this work, we propose Chunked RL, a novel reinforcement learning framework specifically designed for VLA models. Within this framework, we extend temporal difference (TD) learning to incorporate action chunking, a prominent characteristic of VLA models. Building upon this framework, we propose CO-RFT, an algorithm aimed at fine-tuning VLA models using a limited set of demonstrations (30 to 60 samples). Specifically, we first conduct imitation learning (IL) with full parameter fine-tuning to initialize both the backbone and the policy. Subsequently, we implement offline RL with action chunking to optimize the pretrained policy. Our empirical results in real-world environments demonstrate that CO-RFT outperforms previous supervised methods, achieving a 57% improvement in success rate and a 22.3% reduction in cycle time. Moreover, our method exhibits robust positional generalization capabilities, attaining a success rate of 44.3% in previously unseen positions.