Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
arXiv:2603.11653v3 Announce Type: replace-cross Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of C
Overview
arXiv:2603.11653v3 Announce Type: replace-cross Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of CRL for large pretrained VLAs across diverse lifelong RL benchmarks. We find that, contrary to established belief, simple Seq. FT with low-rank adaptation (LoRA) is remarkably strong: it achieves high plasticity, exhibits little to no forgetting, and retains strong zero-shot generalization, frequently outperforming more sophisticated CRL methods. Through detailed analysis, we show that this robustness arises from a synergy between the large pretrained model, parameter-efficient adaptation, and on-policy RL. Together, these components reshape the stability-plasticity trade-off, making continual adaptation both stable and scalable. Our results position Sequential Fine-Tuning as a powerful method for continual RL with VLAs and provide new insights into lifelong learning in the large model era. Code is available at https://github.com/UT-Austin-RobIn/continual-vla-rl
Source
Originally published at arxiv.org.
Related Articles
- Performance Characterization of Frequency-Selective Wireless Power Transfer Toward Scalable Untethered Magnetic Actuation
- Casting Everything to Online API Services? A Survey of Integrating Localized Speech Recognition Models in Robotic Systems
- ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat
Source: https://arxiv.org/abs/2603.11653