视觉强化学习方法研究综述OA

Vision,as the primary means for reinforcement learning agents to perceive their environment,provides rich and detailed information that supports agents in making more complex and precise decisions.However,the high-dimensional nature of visual data often leads to information redundancy and low sample efficiency,posing a key challenge in the application of reinforcement learning.How to efficiently extract key visual representations from limited interaction data to enhance agents'decision-making capabilities has become a current research focus.To ad-dress this,this paper systematically reviews visual reinforcement learning methods,categorizing them into five cat-egories based on their core ideas and implementation mechanisms:Image-enhanced,model-enhanced,task-assisted,knowledge-transferred,and offline visual reinforcement learning approaches.It provides an in-depth analysis of the research progress in each category,as well as the strengths and limitations of representative works.Meanwhile,this paper reviews four major benchmark platforms:DMControl,DMControl-GB,DCS,and RL-ViGen,and summar-izes the applications of visual reinforcement learning in typical scenarios such as robotic control,autonomous driv-ing,and multimodal large models.Finally,based on current research bottlenecks,this paper discusses future devel-opment trends and potential research directions,aiming to offer a clear technical framework and research reference for this field.