Continuous Control

Follow this topic Ask about this topic

Continuous control concerns decisions that unfold over time, from robotic movement and vehicle motion to industrial processes, where actions are continuous-valued rather than discrete. Reinforcement-learning methods such as PPO, SAC, and TD3 learn policies from interaction, while model-based control and model-predictive control use learned or known dynamics to plan ahead; newer work also explores flow- and diffusion-based policies for complex action distributions. Researchers evaluate methods in simulated settings such as MuJoCo and the DeepMind Control Suite, as well as on physical robots and engineered systems. A central challenge is balancing sample efficiency, computation, smooth and safe behavior, and reliable transfer from simulation to real deployment.

Latest papers

57 papers9 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Second Thoughts: Exploring and Planning through Comparative Imagination in World Models
Oct 20, 2026Hieu Tran, Hong YuWorld Model-Based Planning Model-Based RL
University of Massachusetts Amherst · University of Massachusetts Lowell
JAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional Environments
Oct 20, 2026Chaitanya Kaul, Markus Klar, Sebastian Stein +3Active Inference Continuous Control
University of Glasgow, Glasgow, Scotland, UK
Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers
Oct 17, 2026Amir Reza Hariri, Kevin B. Englehart, Erik SchemeContinuous Control EMG-Based Gesture Recognition
Institute of Biomedical Engineering and the Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada.
A Flow-Theoretic Multimodal Control Framework Fusing Mental and Physical Engagement for Upper-Limb Rehabilitation
Oct 15, 2026Jun Leng, Pengcheng Li, Hanze Wang +2Assistive Robotics Continuous Control
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen 518055, China · Aerospace Center Hospital, School of Life Science, and the Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, Beijing 100081, China
Attribution-Gated Joint Estimation of Intention and Capability for Assist-as-Needed Upper-Limb Robots
Oct 15, 2026Pengcheng Li, Shuxiang Guo, Hanze Wang +3Assistive Robotics Continuous Control
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China · Aerospace Center Hospital, School of Life Science, and the Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Beijing Institute of Technology, Beijing, China · Department of Peripheral Vascular Intervention, Aerospace Center Hospital, School of Life Science, Beijing Institute of Technology, Beijing, 100081, China
Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning
Oct 14, 2026Parham Nooranbakht, Seyed Mahdi Basiri Azad, Joschka BödeckerReinforcement Learning Q-Learning
Faculty of Engineering, Department of Computer Science Albert-Ludwigs-Universität Freiburg, Germany
DR-APO: Decoupled-Representation Advantage-Guided Policy Optimization from Continuous Control to Embodied Navigation
Oct 12, 2026Runhua Zhang, Yingjie Niu, Chao LiPolicy Optimization RL for Generative Models
DEEP Robotics, Hangzhou, China · Zhejiang University, Hangzhou, China
Funnel planning and control for manipulators using neural Signed Configuration Distance Functions
Oct 10, 2026Bernhard Wullt, Christos K. Verginis, Per Mattsson +2Safe Motion Planning Kinodynamic Motion Planning
ABB Robotics, Sweden · the Division of Signals and Systems, Department of Electrical Engineering, Uppsala University, Uppsala, Sweden · the Division of Systems and Control, Department of Information Technology, Uppsala University, Uppsala, Sweden
FERPO: Forward Entropy-Regularized Policy Optimization
Oct 1, 2026Sebastian Sanokowski, Alireza Sarmadi, Majid KhadivKL-Regularized RL Policy Optimization
Applied and Theoretical Aspects of Robot Intelligence (ATARI) Lab, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich
SwingRL: Adaptive Observation Reinforcement Learning with World-Model Prediction for Cable-Suspended Hoisting Control
Sep 27, 2026Guangming Wang, Xiaoyu Zhang, Yucheng Xin +8Robotic Control Feedback Control
Department of Engineering, University of Cambridge, Cambridge, CB2 1PZ, U.K. · Tsinghua University, Beijing, China · School of Engineering, Cardiff University, Cardiff, U.K. +1
GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning
Sep 18, 2026Alvaro Serra-Gomez, Thomas MoerlandRL Exploration Model-Based Planning
Leiden Institute of Advanced Computer Science, Leiden University, 2311 EZ Leiden, The Netherlands
REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement
Sep 17, 2026Sachini Weerasekara, Sagar Kamarthi, Jacqueline IsaacsRL Control Reinforcement Learning
Northeastern University, Boston, MA, USA.
GR2PO: Group Relative Return Policy Optimization for Continuous Robot Control
Sep 17, 2026Pengqin Wang, Qiming Zhang, Shaojie Shen +1Reinforcement Learning Group Relative Policy Optimization
Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Division of Emerging Interdisciplinary Areas, the Hong Kong University of Science and Technology, Hong Kong SAR, China · Intelligent Transportation Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1
Refinement-Based Flow Policy Optimization
Sep 14, 2026Bumgeun Park, Hyukjun Yang, Donghwan LeeRL Control Flow Matching
Korea Advanced Institute of Science and Technology (KAIST)
On Global Regulatability of Robot Manipulators by Classical PID
Sep 1, 2026Cheng Zhao, Jingru Zhu, Lei GuoRobotic Control Feedback Control
State Key Laboratory of Mathematical Sciences, AMSS, Chinese Academy of Sciences, Beijing 100190, China · School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade
Aug 28, 2026Nicola C. Amorisco, Kamran Pentland, Adriano Agnello +12Continuous Control
United Kingdom Atomic Energy Authority, Culham Campus, Abingdon, Oxfordshire, OX14 3DB, United Kingdom · STFC Hartree Centre, Sci-Tech Daresbury, Keckwick Lane, Daresbury, Warrington, WA4 4AD, United Kingdom
Real-time virtual circuits for plasma shape control via neural network emulators: integration and testing in the MAST-U PCS
Aug 26, 2026Matthew J. Marshall, Edward Jones, Graham J. McArdle +10AI Control Feedback Control
Hartree Centre, STFC, Daresbury Laboratory, Daresbury, WA4 4AD, United Kingdom · UKAEA, Culham Campus, Abingdon, OX14 3DB, United Kingdom
An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World Models
Aug 18, 2026Javier Aguilar MartínCode World Models World Models
AGILabs
CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation
Aug 15, 2026Peng Jia, Li Dai, Zhen Xiao +2Talking Head Generation Audio-Driven Facial Animation
Hefei University of Technology, Hefei 230009, Anhui, China
Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control
Aug 7, 2026Qi Zhao, Guozheng Ma, Yilun Kong +9Reinforcement Learning Experience Replay
Tsinghua University · Nanyang Technological University · Mila - Quebec Artificial Intelligence Institute +1
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
Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control
Aug 5, 2026Rohit Kumar Salla, Manoj Saravanan, Simon StepputtisDiffusion Policy Continuous Control
Virginia Polytechnic Institute and State University (Virginia Tech), Blacksburg, Virginia, USA
Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings
Jul 30, 2026Christian RosenthalLanguage Model-Based Control Safety-Critical Control
Sole author — independent research, industrial AI methodology
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?
Jul 29, 2026Perry Dong, Ron Polonsky, Dorsa Sadigh +1Continuous Control RL Fine-Tuning
Stanford University
Sensor-Placement-Agnostic Sonomyography: Toward Continuous High-Dimensional Control by Users with Tetraplegia
Jul 29, 2026Gavin Sueltz, Vikram Athithan, Emma Ferran +3Wearable Sensing Assistive Robotics
Departments of Mechanical Engineering and Physical Medicine & Rehabilitation, the Kahlert School of Computing, and the Robotics Center at the University of Utah, Salt Lake City, UT 84112, USA
Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning
Jul 6, 2026Idan Lev-Yehudi, Vadim IndelmanAdaptive Sampling Graph-Based Planning
Technion Autonomous Systems Program (TASP), Technion – Israel Institute of Technology · Stephen B. Klein Faculty of Aerospace Engineering, Technion – Israel Institute of Technology · Faculty of Data and Decision Sciences, Technion – Israel Institute of Technology
Low-power analogue neural networks with trainable nonlinear connections for continuous control
Jun 21, 2026Ian T. Vidamour, Fernando Aguirre, Thomas J. Hayward +13Efficient Neural Network Inference Kolmogorov-Arnold Networks
School of Computer Science, University of Sheffield, Sheffield, S1 4DP, United Kingdom · Intrinsic Semiconductor Technologies, London, United Kingdom · School of Chemical, Biological, and Materials Science Engineering, University of Sheffield, Sheffield, S1 3JD, United Kingdom +5
Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control
Jun 19, 2026Yueci DengRobotic RL Policy Gradient Methods
School of Data Science, The Chinese University of Hong Kong, Shenzhen
Interaction Dynamics MPC for Knee Rehabilitation Exoskeletons: A Closed-Loop SEA Outer-Loop Study
Jun 11, 2026Yongyan Cao, Jinshan TangRobotic Control Model Predictive Control
Voryx Robotics · George Mason University, Dept. of Health Administration and Policy
Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control
Jun 7, 2026Boai Sun, Wenjin Guo, Zongmin Yu +1Robotic Control Continuous Control
National University of Singapore, Singapore.

Oct 20, 2026J/K move · Enter open · S save

Second Thoughts: Exploring and Planning through Comparative Imagination in World Models

Hieu Tran, Hong Yu

University of Massachusetts Amherst · University of Massachusetts Lowell

World Model-Based Planning Model-Based RL RL Exploration Continuous Control

Open paper AskPDF arXiv

World models let agents compare imagined outcomes before acting, but an agent must still decide which alternatives to explore and when a proposed plan should replace its learned policy. We introduce SDI (Sibling Disagreement in Imagination), which connects these decisions through a shared actor-based reference. SDI compares action sequences imagined from the same model state, using repeated rollouts of the actor's own sequence to measure variation under fixed behavior. This reference scales both the spread across candidate returns, which provides an exploration signal, and a proposed plan's predicted advantage, which governs action acceptance. The agent executes a planned action when its advantage exceeds the reference variability by a fixed factor; otherwise, it follows the actor. SDI reuses the base agent's world model, actor, and critic without requiring an additional disagreement ensemble. Exploration and planning guide training data collection, while evaluation uses the learned actor alone. Across Meta-World, Adroit, and DM-Control, SDI achieves a higher observed task-average score than every compared baseline in each suite and matches or exceeds the strongest baseline's performance on 15 of 18 tasks. Component ablations and robustness analyses further examine the roles of exploration, planning exposure, and action acceptance. Paired evaluations from identical simulator states show that the gate improves both recovery from actor failures and preservation of successful behavior relative to ungated planning, while substantially reducing return degradation. Together, these results support comparing imagined alternatives against a shared actor reference as a unified approach to exploring and planning with world models.