English
Related papers

Related papers: WMPO: World Model-based Policy Optimization for Vi…

200 papers

Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and efficiency. Existing approaches either solely optimize…

Computation and Language · Computer Science 2025-03-14 Siyin Wang , Zhaoye Fei , Qinyuan Cheng , Shiduo Zhang , Panpan Cai , Jinlan Fu , Xipeng Qiu

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low…

Computation and Language · Computer Science 2025-06-12 Siheng Li , Zhanhui Zhou , Wai Lam , Chao Yang , Chaochao Lu

Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can…

Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve…

Robotics · Computer Science 2021-03-08 Daniël Willemsen , Mario Coppola , Guido C. H. E. de Croon

Vision-Language-Action~(VLA) models have shown strong potential for general-purpose robotic manipulation, yet they still struggle to generalize to unseen tasks that necessitate transferring relevant experience across objects, scenes, and…

Robotics · Computer Science 2026-05-29 Shengyu Si , Yuanzhuo Lu , Ruimeng Yang , Ziyi Ye , Zuxuan Wu , Yu-Gang Jiang

Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Wenyao Zhang , Hongsi Liu , Zekun Qi , Yunnan Wang , Xinqiang Yu , Jiazhao Zhang , Runpei Dong , Jiawei He , Fan Lu , He Wang , Zhizheng Zhang , Li Yi , Wenjun Zeng , Xin Jin

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which…

Robotics · Computer Science 2026-03-09 Liangzhi Shi , Shuaihang Chen , Feng Gao , Yinuo Chen , Kang Chen , Tonghe Zhang , Hongzhi Zang , Weinan Zhang , Chao Yu , Yu Wang

Capturing latent variations ("contexts") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control problem and formally characterize two properties and their…

Machine Learning · Computer Science 2025-07-28 Yuliang Gu , Hongpeng Cao , Marco Caccamo , Naira Hovakimyan

The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demonstrated strong generalization across diverse manipulation tasks, yet pretrained policies…

Robotics · Computer Science 2026-05-26 Perry Dong , Kuo-Han Hung , Tian Gao , Dorsa Sadigh , Chelsea Finn

Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or…

Machine Learning · Computer Science 2024-05-30 Yu Luo , Tianying Ji , Fuchun Sun , Jianwei Zhang , Huazhe Xu , Xianyuan Zhan

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Artificial Intelligence · Computer Science 2025-10-02 Yunhao Wang , Ziting Li , Shuai Chen , Tao Liu , Chao Song , Junjie Jiang , Jian Zhu , Peng Gao , Bin Qin

Recent studies have demonstrated that Reinforcement Learning (RL), notably Group Relative Policy Optimization (GRPO), can intrinsically elicit and enhance the reasoning capabilities of Vision-Language Models (VLMs). However, despite the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Xinyu Tian , Shu Zou , Zhaoyuan Yang , Mengqi He , Peter Tu , Jing Zhang

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions…

Machine Learning · Computer Science 2025-10-03 Weizhe Chen , Sven Koenig , Bistra Dilkina

Vision-Language-Action (VLA) models empower robots to understand and execute tasks described by natural language instructions. However, a key challenge lies in their ability to generalize beyond the specific environments and conditions they…

The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…

Machine Learning · Computer Science 2021-08-10 Oleh Rybkin , Chuning Zhu , Anusha Nagabandi , Kostas Daniilidis , Igor Mordatch , Sergey Levine

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…

Computation and Language · Computer Science 2026-05-26 Yihong Tang , Kehai Chen , Liang Yue , Benyou Wang , Min Zhang

Blind Face Restoration (BFR) encounters inherent challenges in exploring its large solution space, leading to common artifacts like missing details and identity ambiguity in the restored images. To tackle these challenges, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Bin Wu , Yahui Liu , Chi Zhang , Yao Zhao , Wei Wang

We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic manipulation tasks where good but imperfect controllers are…

Robotics · Computer Science 2019-01-04 Tom Silver , Kelsey Allen , Josh Tenenbaum , Leslie Kaelbling

Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit…

Machine Learning · Computer Science 2026-04-16 Angelo Moroncelli , Roberto Zanetti , Marco Maccarini , Loris Roveda

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Yang Li , Xinyu Fang , Shengyuan Ding , Peiji Li , Yongkang Chen , Yichuan Ma , Tianyi Lyu , Linyang Li , Dahua Lin , Qipeng Guo , Qingwen Liu , Kai Chen