What Can RL Bring to VLA Generalization? An Empirical Study

• URL: http://arxiv.org/abs/2505.19789v2
• Date: Wed, 11 Jun 2025 05:27:58 GMT
• Title: What Can RL Bring to VLA Generalization? An Empirical Study
• Authors: Jijia Liu, Feng Gao, Bingwen Wei, Xinlei Chen, Qingmin Liao, Yi Wu, Chao Yu, Yu Wang,
• Abstract summary: Large Vision-Language Action (VLA) models have shown significant potential for embodied AI.<n>Their predominant training via supervised fine-tuning (SFT) limits generalization due to compounding errors under distribution shifts.<n>Our study introduces a comprehensive benchmark for evaluating VLA generalization and systematically investigates the impact of RL fine-tuning.
• Score: 42.58811485942049
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding errors under distribution shifts. Reinforcement learning (RL) offers a path to overcome these limitations by optimizing for task objectives via trial-and-error, yet a systematic understanding of its specific generalization benefits for VLAs compared to SFT is lacking. To address this, our study introduces a comprehensive benchmark for evaluating VLA generalization and systematically investigates the impact of RL fine-tuning across diverse visual, semantic, and execution dimensions. Our extensive experiments reveal that RL fine-tuning, particularly with PPO, significantly enhances generalization in semantic understanding and execution robustness over SFT, while maintaining comparable visual robustness. We identify PPO as a more effective RL algorithm for VLAs than LLM-derived methods like DPO and GRPO. We also develop a simple recipe for efficient PPO training on VLAs, and demonstrate its practical utility for improving VLA generalization. The project page is at https://rlvla.github.io

Related papers

• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Perception-Aware Policy Optimization for Multimodal Reasoning [79.56070395437898]
  A major source of error in current multimodal reasoning lies in the perception of visual inputs.<n>We propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason.<n>We observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO.
  arXiv  Detail & Related papers  (2025-07-08T23:22:34Z)
• Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation [19.48826538310603]
  We introduce LVLM to Policy (LVLM2P), a framework that distills knowledge from large vision-language models (LVLM) into more efficientReinforcement Learning agents.<n>Our approach leverages the LVLM as a teacher, providing instructional actions based on trajectories collected by the RL agent.<n>We show that LVLM2P significantly enhances the sample efficiency of baseline RL algorithms.
  arXiv  Detail & Related papers  (2025-05-16T13:15:54Z)
• Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes Better [0.3021678014343889]
  Supervised learning (SL) and reinforcement learning (RL) are widely used to train general-purpose agents for complex tasks.<n>This paper provides a direct comparison between SL and RL in terms of zero-shot generalization.
  arXiv  Detail & Related papers  (2025-03-19T21:03:27Z)
• Refined Policy Distillation: From VLA Generalists to RL Experts [18.186499704928092]
  We present Refined Policy Distillation (RPD), an RL-based policy refinement method.<n>RPD enables the RL agent to learn expert policies that surpass the teacher's performance in both dense and sparse reward settings.<n>Our approach is even robust to changes in the camera perspective and can generalize to task variations that the underlying VLA cannot solve.
  arXiv  Detail & Related papers  (2025-03-06T12:52:11Z)
• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning [104.27224674122313]
  Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions.
  arXiv  Detail & Related papers  (2024-11-17T01:16:37Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization [0.0]
  We introduce a method to address goal misgeneralization in reinforcement learning (RL) Goal misgeneralization occurs when an agent retains its capabilities out-of-distribution yet pursues a proxy rather than the intended one. This study demonstrates how the Large Language Model can efficiently supervise RL agents.
  arXiv  Detail & Related papers  (2024-01-14T01:09:48Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)

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.