RL Control

RL: Reinforcement Learning

Ask about this topic

Overview

Reinforcement learning control studies how agents can learn actions that steer dynamic systems toward goals while managing costs, constraints, and uncertainty. Common approaches include actor-critic methods such as PPO, SAC, and TD3; model-based learning with predictive control; and offline learning from logged data, often combined with safety filters or physical models. Work spans simulated benchmarks and applications such as robotics, traffic, buildings, power grids, and fluid flow, with evaluation increasingly testing hardware transfer and changing conditions. A central tension is that high simulated reward or average performance does not ensure safe, reliable behavior under real-world disturbances, limited data, or distribution shift.

Latest papers

CardsList

276 papers34 papers in the last four weeks, up 13% on the four weeks before. 0.2% of all new papers.

  1. Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control

    Dec 3, 2024Yaron Veksler, Sharon Hornstein, Han Wang +2RL ControlIntelligent Transportation Systems

    Research and Development Labs, General Motors, Herzliya, Israel. · Department of Civil and Environmental Engineering, UC Berkeley.

  2. Constrained Reinforcement Learning for Safe Heat Pump Control

    Sep 29, 2024Baohe Zhang, Lilli Frison, Thomas Brox +1RL ControlConstrained RL

    Faculty of Computer Science, University of Freiburg, Germany · Systems Control and Optimization Laboratory, Department of Microsystems Engineering, University of Freiburg, Germany

  3. Training Verifiably Robust Agents Using Set-Based Reinforcement Learning

    Aug 17, 2024Manuel Wendl, Lukas Koller, Tobias Ladner +1RL ControlReinforcement Learning

    Technical University of Munich, Germany

  4. Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

    Jul 21, 2024Sheila Schoepp, Mehran Taghian, Shotaro Miwa +3RL ControlReinforcement Learning

    Department of Computing Science, University of Alberta, 8900 114 St NW, Edmonton, Alberta, T6G 2S4, Canada · Advanced Technology R&D Center, Mitsubishi Electric Corporation, 8-1-1,Tsukaguchi-honmachi, Amagasaki-shi, Hyogo, 661-8661, Japan · Information Technology R&D Center, Mitsubishi Electric Corporation, 5-1-1, Ofuna, Kamakura-shi, Kanagawa, 247-8501, Japan +1

  5. PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learning

    Mar 9, 2024Mojtaba Taherisadr, Salma ElmalakiRL ControlCyber-Physical Systems

    University of California, Irvine, USA

  6. Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives

    Apr 20, 2023Lening Li, Zhentian Qian, Jianan Xia +7RL ControlReinforcement Learning

    Ningbo University, Ningbo, China · Robotics Engineering Program, Worcester Polytechnic Institute, Worcester, MA, USA · Ningbo Zhenhai Silver-Ball Bearing Co., Ltd., Ningbo, China