VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

2022-02-17 · Che Wang, Xufang Luo, Keith Ross, Dongsheng Li

We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks. We analyze a number of major obstacles in taking a data-driven approach, and present a suite of design principles, novel findings, and critical insights about data-driven visual DRL. Our framework has three stages: in stage 1, we leverage non-RL datasets (e.g. ImageNet) to learn task-agnostic visual representations; in stage 2, we use offline RL data (e.g. a limited number of expert demonstrations) to convert the task-agnostic representations into more powerful task-specific representations; in stage 3, we fine-tune the agent with online RL. On a set of challenging hand manipulation tasks with sparse reward and realistic visual inputs, compared to the previous SOTA, VRL3 achieves an average of 780% better sample efficiency. And on the hardest task, VRL3 is 1220% more sample efficient (2440% when using a wider encoder) and solves the task with only 10% of the computation. These significant results clearly demonstrate the great potential of data-driven deep reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2202.10324

Code (1)

facebookresearch/drqv2 공식 구현 pytorch

Tasks

Deep Reinforcement LearningOffline RL reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MMRPT: MultiModal Reinforcement Pre-Training via Masked Vision-Dependent Reasoning

2025-12-08 · Xuhui Zheng, Kang An, Ziliang Wang, Yuhang Wang 외 arxiv

Multimodal pre-training remains constrained by the descriptive bias of image-caption pairs, leading models to favor surface linguistic cues over grounded visual understanding. We introduce MMRPT, a masked multimodal rein…

Reinforcement Learning Visual Grounding Visual Reasoning

E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis

2026-06-22 · Sijing Li, Zhongwei Qiu, Zhuoya Wang, Boxiang Yun 외 arxiv

While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data. Current Supervised Fine-Tuning (SFT…

Medical Report Generation Reinforcement Learning

RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning

2025-08-17 · Suhang Hu, Wei Hu, Yuhang Su, Fan Zhang arxiv

Vision-Language Models (VLMs) struggle with complex image annotation tasks, such as emotion classification and context-driven object detection, which demand sophisticated reasoning. Standard Supervised Fine-Tuning (SFT) …

Reinforcement Learning Emotion Classification Object Detection

VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection

2025-05-26 · Zeyi Huang, Yuyang Ji, Anirudh Sundara Rajan, Zefan Cai 외

We introduce VisTA, a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and combine tools from a diverse library based on empirical performance. Existing methods for tool-au…

Diversity reinforcement-learning Reinforcement Learning Visual Reasoning

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

2026-02-05 · Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao 외 arxiv

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely lang…

Reinforcement Learning