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

• URL: http://arxiv.org/abs/2508.02219v1
• Date: Mon, 04 Aug 2025 09:11:48 GMT
• Title: CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
• Abstract summary: We propose Chunked RL, a novel reinforcement learning framework for Vision-Language-Action (VLA) models.<n>Within this framework, we extend temporal difference (TD) learning to incorporate action chunking, a prominent characteristic of VLA models.<n>We then propose CO-RFT, an algorithm aimed at fine-tuning VLA models using a limited set of demonstrations.
• Score: 7.780242426487376
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning [15.872908522637957]
  We introduce a novel, plug-and-play fine-tuning pipeline for Vision-Language-Action (VLA) models.<n>We conceptualize VLA-generated actions as a unified interface, upon which we train a residual policy.<n>Within only 1.5 hour of real-world online RL training, the average success rate exceeds 95% on real robots.
  arXiv  Detail & Related papers  (2026-06-22T05:07:08Z)
• EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models [84.73890225707264]
  We present EXPO-FT, a system for stable, sample-efficient RL finetuning of pretrained VLA policies.<n>Our system achieves perfect task performance (30/30 successes) across all evaluated tasks within an average of 19.1 minutes of online robot data.<n>We release an open-source robustness with the aim of facilitating broader adoption of RL finetuning of VLA models in robotics.
  arXiv  Detail & Related papers  (2026-05-25T06:31:03Z)
• Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning [26.103428215400697]
  We find that simple Sequential Fine-Tuning (Seq. FT) with low-rank adaptation (LoRA) is remarkably strong.<n>Our results position Sequential Fine-Tuning as a powerful method for continual RL with Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2026-03-12T08:22:39Z)
• VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model [87.75549463328836]
  The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction.<n>We propose a simple iterative improvement algorithm that uses real-world roll-out data to improve the fidelity of the world model.<n>We achieve a 39.2% absolute success rate improvement over the base policy and 11.6% improvement from training with the generated synthetic rollouts.
  arXiv  Detail & Related papers  (2026-02-12T15:21:47Z)
• Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning [34.29473529235131]
  LifeLong-RFT is a simple yet effective Reinforcement Fine-Tuning (RFT) strategy for VLA models.<n>LifeLong-RFT integrates chunking-level on-policy reinforcement learning with the proposed Multi-Dimensional Process Reward (MDPR) mechanism.<n>Our method achieves a 22% gain in average success rate over SFT, while effectively adapting to new tasks using only 20% of the training data.
  arXiv  Detail & Related papers  (2026-02-11T04:05:03Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• Self-Improving Vision-Language-Action Models with Data Generation via Residual RL [29.682761652941963]
  Probe, Learn, Distill (PLD) is a three-stage plug-and-play framework that improves vision-language-action models.<n>PLD achieves near-saturated 99% task success on LIBERO, over 50% gains in SimplerEnv, and 100% success on real-world Franka and YAM arm manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-30T06:24:04Z)
• Internalizing World Models via Self-Play Finetuning for Agentic RL [65.96875390986655]
  Large Language Models (LLMs) as agents often struggle in out-of-distribution (OOD) scenarios.<n>We show how to encode this world model by decomposing it into two components: state representation and transition modeling.<n>We introduce SPA, a simple reinforcement learning framework that cold-starts the policy via a Self-Play supervised finetuning stage to learn the world model.
  arXiv  Detail & Related papers  (2025-10-16T18:03:39Z)
• RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models [11.688277445120567]
  Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks.<n>Their substantial parameter sizes and high inference latency pose significant challenges for real-world deployment.<n>We propose RLRC, a three-stage recovery method for compressed VLAs.
  arXiv  Detail & Related papers  (2025-06-21T08:45:32Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning [14.099306230721245]
  We present VLA-RL, an exploration-based framework that improves on online collected data at test time.<n>We fine-tune a pretrained vision-language model as a robotic process reward model, which is trained on pseudo reward labels annotated on automatically extracted task segments.<n>VLA-RL enables OpenVLA-7B to surpass the strongest finetuned baseline by 4.5% on 40 challenging robotic manipulation tasks in LIBERO.
  arXiv  Detail & Related papers  (2025-05-24T14:42:51Z)
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success [100.226572152954]
  We present an optimized fine-tuning recipe for vision-language-action models (VLAs)<n>Our recipe boosts OpenVLA's average success rate across four task suites from 76.5% to 97.1% while increasing action generation throughput by 26$times$.<n>In real-world evaluations, our fine-tuning recipe enables OpenVLA to successfully execute dexterous, high-frequency control tasks on a bimanual ALOHA robot.
  arXiv  Detail & Related papers  (2025-02-27T00:30:29Z)
• ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy [10.596344084789434]
  Vision-Language-Action (VLA) models have shown substantial potential in real-world robotic manipulation.<n>Fine-tuning these models through supervised learning struggles to achieve robust performance due to limited, inconsistent demonstrations.<n>We propose a reinforced fine-tuning approach for VLA models, named ConRFT, which consists of offline and online fine-tuning.
  arXiv  Detail & Related papers  (2025-02-08T05:01:17Z)
• Improving Vision-Language-Action Model with Online Reinforcement Learning [17.043068379668842]
  Recent studies have successfully integrated large vision-language models into low-level robotic control by supervised fine-tuning.<n>We propose iRe-VLA framework, which iterates between Reinforcement Learning and Supervised Learning to effectively improve VLA models.
  arXiv  Detail & Related papers  (2025-01-28T02:53:48Z)
• Efficient Continual Pre-training by Mitigating the Stability Gap [68.49269649759005]
  We study the behavior of Large Language Models (LLMs) during continual pre-training. We propose three effective strategies to enhance LLM performance within a fixed compute budget. Our strategies improve the average medical task performance of the OpenLlama-3B model from 36.2% to 40.7% with only 40% of the original training budget.
  arXiv  Detail & Related papers  (2024-06-21T02:28:37Z)
• A Critical Evaluation of AI Feedback for Aligning Large Language Models [60.42291111149438]
  We show that simple supervised fine-tuning with GPT-4 as the teacher outperforms existing RLAIF pipelines. More generally, we find that the gains from RLAIF vary substantially across base model families, test-time evaluation protocols, and critic models.
  arXiv  Detail & Related papers  (2024-02-19T18:53:54Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations [36.44386146801296]
  Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications. We find that leveraging just a handful of demonstrations can dramatically improve the sample-efficiency of model-based RL. We empirically study three complex visuo-motor control domains and find that our method is 150%-250% more successful in completing sparse reward tasks.
  arXiv  Detail & Related papers  (2022-12-12T04:28:50Z)
• Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective [142.36200080384145]
  We propose a single objective which jointly optimize a latent-space model and policy to achieve high returns while remaining self-consistent. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods.
  arXiv  Detail & Related papers  (2022-09-18T03:51:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.