Visual RL

RL: Reinforcement Learning

Visual reinforcement learning studies how agents can learn control policies from images, video, or other visual observations rather than relying on fully specified state variables. Common approaches include learning compact task-relevant representations, building predictive world models for planning, and improving exploration or reward signals when feedback is sparse. Methods are tested on settings such as DeepMind Control Suite, Atari, Procgen, MetaWorld, visual navigation, and robotic manipulation, with sim-to-real transfer an important goal. A central challenge is balancing sample and compute efficiency with robustness to visual distractions and shifts between training and deployment environments.

Latest papers

59 papers8 papers in the last four weeks, up 60% on the four weeks before. 0.0% of all new papers.

Computer Vision Navigation for an Autonomous Vehicle Model Using Reinforcement Learning
Oct 24, 2026Dinis Fernandes, Tiago Ribeiro, António Ribeiro +3RL for Autonomous Driving RL Control
Lab. Automação e Robótica University of Minho Guimarães, Portugal
Dynamics-Aligned Representation Learning under Induced Partial Observability
Oct 18, 2026SM Mazharul Islam, Manfred HuberModel-Based RL Representation Learning for RL
Department of Computer Science and Engineering, University of Texas at Arlington, TX-76019, USA
AgentGarten: Code Worlds for Evolving Agents
Oct 8, 2026Jiawei Chi, Shangchen Miao, Zhiyuan Shi +12Self-Evolving Agents Neural Rendering
MirroS Lab
FOCUS: From Privileged States to RGB-D with Controlled Modality Switching and Representation Alignment
Oct 8, 2026Filip Grigorov, Kourosh Darvish, Nandita VijaykumarRobotic RL Visual RL
University of Toronto Canada
Directed Temporal Representations for Offline Visual Control
Oct 6, 2026Chenyang Yuan, Haoyu Wang, Zhuo Sun +1Visual RL Trajectory Representation Learning
University of Sheffield · Shanghai Jiao Tong University · Shanghai University of Finance and Economics +1
Same Reward, Different Skills: When Multimodal RL Learns to Look
Oct 1, 2026Haocun Ye, Xinlong Jiang, Qile Chen +6Reinforcement Learning with Verifiable Rewards Visual Grounding
University of the Chinese Academy of Sciences · Institute of Computing Technology, Chinese Academy of Sciences · Independent Researcher
Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies
Sep 29, 2026Irving Giovani Bronzatti Petrazzini, Eric Aislan AntoneloImitation Learning Behavior Cloning
Department of Automation and Systems Engineering, Federal University of Santa Catarina, Florian´opolis, Santa Catarina, Brazil.
SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents
Sep 29, 2026Shengtian Yang, Ziyu Xiong, Kaibing Yang +6Reinforcement Learning RL for GUI Agents
Southeast University, Nanjing, China · Kuaishou Technology, Beijing, China · Unaffiliated
StarWM: Self-Supervised Trained Attention Routing for Robust World Models
Sep 25, 2026Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte +4Attention Routing World Model Learning
Ulm University · German Aerospace Center (DLR)
Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement
Sep 15, 2026Tobias Schaffer, Mohab Elkhayat, Daniela Nicklas +2RL for Robotics Intrinsic Reward Methods
Technology Campus Cham - Intelligent Robotics, Deggendorf Institute of Technology, Cham, Germany
LettuceVisSim: A Simulator That Generates Lettuce Image Time-series for Vision-Based Reinforcement Learning
Sep 11, 2026Ziye Zhu, Bert van 't Ooster, Congcong Sun +2Synthetic Data Generation Image Generation
Agricultural Biosystems Engineering Group, Wageningen University & Research, The Netherlands · Biometris, Wageningen University & Research, The Netherlands
Learning to Fly: Stable Vision-Guided UAV Servoing with Compact Target-Centric Cues and Reinforcement Learning
Sep 7, 2026Saurbh Singh Jamwal, Nived ChebroluVision-Based Robot Control Aerial Robotics
Department of Computer Science and Engineering Indian Institute of Technology Bombay
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Sep 1, 2026Giovanni Bonetta, Matteo Merler, Davide Zago +2Uncertainty Sampling Visual RL
Department of Computer Science, University of Torino, Torino, Italy · Natural Language Processing Unit, Fondazione Bruno Kessler, Trento, Italy
CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents
Aug 21, 2026Jiancheng Wang, Mingli Zhu, Tong Zhang +4Adversarial Attacks Visual RL
Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement Learning
Aug 18, 2026Hoda Yamani, Henry Williams, Bruce A. MacDonaldPrioritized Experience Replay Reinforcement Learning
Robot Learning Team and CARES Robotics Lab, Department of Electrical, Computer, and Software Engineering, University of Auckland, Auckland, New Zealand.
FLEET: Token-Based Feature Extraction for Event Camera-based Reinforcement Learning
Aug 17, 2026Tristan Gottwald, Maximilian Schier, Melanie Schaller +1Representation Learning for RL Event-Based Vision
Institute of Information Processing, L3S, Leibniz University Hannover, Germany
Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System
Aug 17, 2026Alam Noor, Luis Almeida, Kai Li +3Aerial Robotics Edge Computing
CISTER Research Center, Porto, Portugal. · Instituto de Telecomunicac¸˜oes, Faculdade de Engenharia, Universidade do Porto, Portugal. · Department of Information Technology, Kennesaw State University, USA. +2
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
Aug 8, 2026Donghu Kim, Youngdo Lee, Hojoon Lee +6Reinforcement Learning Visual RL
KAIST · Mila – Québec AI Institute · Université de Montréal +2
Aftab: A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning
Aug 7, 2026Taha Shieenavaz, Shabnam Zareshahraki, Loris NanniDeep Q-Learning Q-Learning
Department of Information Engineering, University of Padua, Italy
TaskSense: Focusing on What Matters in World Models
Aug 6, 2026SM Mazharul Islam, Manfred HuberWorld Model Learning World Models
1The University of Texas at Arlington
Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
Aug 6, 2026Xinwei Liu, Junyuan Liang, Jianting Zhang +1Predictive Representation Learning Continuous Control
Sun Yat-sen University · Purdue University
Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter
Jul 26, 2026Yuchao Mei, Guohao Zhang, Luxia Ai +2Collision Avoidance Risk-Sensitive RL
National Key Laboratory of Science and Technology on Multi-spectral Information Processing, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
Jul 20, 2026Daegyeong Roh, Juho Bae, Han-Lim ChoiMahalanobis Distance Metric Learning
Department of Aerospace Engineering, Korea Advanced Institute of Science and Technology, Daejon, Republic of Korea.
Difference-Based Relational Learning for Zero-Shot Object-Goal Visual Navigation With Direct Sim-to-Real Transfer
Jul 17, 2026Guolei Qi, Feitian ZhangZero-Shot Learning Representation Learning
Guolei Qi and Feitian Zhang*
UniVR: Thinking in Visual Space for Unified Visual Reasoning
Jul 14, 2026Zhongwei Ren, Yunchao Wei, Yao Zhao +5Physical Reasoning Visual Spatial Reasoning
Beijing Jiaotong University · ByteDance
Mask-based Predictive Representations for Reinforcement Learning
Jul 5, 2026Kai ZhaoRepresentation Learning Predictive Representation Learning
School of Systems Science, Beijing Normal University · Beijing, China
Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos
Jul 1, 2026Jinwen Wang, Youfang Lin, Xiaobo Hu +2Cross-Embodiment Robot Learning Robotic RL
Beijing Jiaotong University, China · Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, China
Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization
Jul 1, 2026Jinwen Wang, Youfang Lin, Xiaobo Hu +4Representation Learning Representation Learning for RL
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science & Technology, Beijing Jiaotong University, China · CSSC Intelligent Innovation Research Institute, China and Zhejiang University, China
Stage-Transition Dense Reward Modeling for Reinforcement Learning
Jun 30, 2026Yang Yang, Bingjie Chen, Zihan Wang +4RL for Robotics Long-Horizon Robotic Manipulation
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China. · Zerith Robotics, Shenzhen 518055, China.
Staged Hybridisation for Visual Quantum Reinforcement Learning via Knowledge Distillation
Jun 29, 2026Javier Lazaro, Juan-Ignacio Vazquez, Pablo Garcia-BringasHybrid Quantum-Classical ML Variational Quantum Circuits
University of Deusto, Bilbao, Spain · FSAS International Quantum Center, Fujitsu

Oct 24, 2026J/K move · Enter open · S save

Computer Vision Navigation for an Autonomous Vehicle Model Using Reinforcement Learning

Dinis Fernandes, Tiago Ribeiro, António Ribeiro, Carolina Lopes+2

Lab. Automação e Robótica University of Minho Guimarães, Portugal

RL for Autonomous Driving RL Control Visual RL

Open paper AskPDF arXiv

This work aims to assess the capabilities of the reinforcement learning algorithm, Proximal Policy Optimization (PPO), in developing a policy capable of controlling the speed and steering angle of a vehicle model to navigate within simulated road lines. The control system's input is a camera, and its outputs are the rotational speed of the rear wheels and the steering angle of the front wheels, controlling the vehicle's speed and direction, respectively. The algorithm is trained and tested in a simulated environment, where it receives image frames from the vehicle's camera, processes them through a feature extraction algorithm, and feeds them into the policy. For each frame, the policy outputs speed and direction commands for the vehicle. The policy is iteratively updated to enhance its performance. The reinforcement learning algorithm successfully generates a policy capable of navigating the vehicle in a simplified environment. Potential improvements are suggested to enhance the system's robustness in more complex scenarios. Creating a simulation environment suitable for testing an advanced reinforcement learning algorithm is a complex task. This project offers a framework for other developers to test different approaches and algorithms. The tested algorithm, PPO, uses proximity intervals - an innovative approach in reinforcement learning. In some scenarios, the algorithm achieved better performance than predecessor algorithms, which are typically harder to implement and require tuning more hyperparameters.