Continuous Control

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

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
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
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.
PRISM: PRior-guided Imagination Sampling in world Models
Jun 6, 2026Yuhai Wang, Jiawei Xia, Rongxuan Zhou +4World Models for Robotics World Model-Based Planning
1Northeastern University · University of California, Berkeley · 3Qiyuan Lab +1
Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
Jun 4, 2026Johan Obando-Ceron, Lu Li, Scott Fujimoto +3Reinforcement Learning Representation Learning for RL
Mila – Québec AI Institute · Université de Montréal · McGill University +2
Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control
May 22, 2026Shuai Zhen, Yifan Zhang, Yuling Wang +1RL Control Reinforcement Learning
Beijing University of Posts and Telecommunications · Hangzhou Dianzi University
PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
May 20, 2026Richa Verma, Bavish Kulur, Sanjay Chawla +1Direct Preference Optimization Constrained RL
TCS Research, Department of CSE, IIT Madras India · Department of Computing Science, University of Alberta Canada · Qatar Computing Research Institute, Hamad Bin Khalifa University Qatar +1
Implicit Action Chunking for Smooth Continuous Control
May 19, 2026Bosun Liang, Shuo Pei, Zirui Chen +5RL Control Continuous Control
Department of Data and Systems Engineering, The University of Hong Kong, Hong Kong SAR, China · Beijing Institute of Technology, Zhuhai, China · College of Computer Science, Sichuan University, Chengdu, China
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
May 15, 2026Thomas Evers, Cristian Meo, Wendelin Bohmer +2Model Predictive Control Continuous Control
TU Delft · LatentWorlds AI
Real-time virtual circuits for plasma shape control via neural network emulators
May 14, 2026Alasdair Ross, George K. Holt, Kamran Pentland +7Neural Surrogate Modeling Feedback Control
STFC Hartree Centre, Sci-Tech Daresbury, Keckwick Lane, Daresbury, Warrington, WA4 4AD, United Kingdom · United Kingdom Atomic Energy Authority, Culham Campus, Abingdon, Oxfordshire, OX14 3DB, United Kingdom
Debiased Model-based Representations for Sample-efficient Continuous Control
May 12, 2026Jiafei Lyu, Zichuan Lin, Scott Fujimoto +5Representation Learning Continuous Control
1Tencent Hunyuan · 2McGill University · School of Computer
Beyond Self-Play: Hierarchical Reasoning for Continuous Motion in Closed-Loop Traffic Simulation
May 9, 2026Weifan Zhang, Xiaofeng Zhao, Adel Bazzi +3Human Behavior Simulation Hierarchical RL
Isuzu Technical Center of America, Plymouth, MI, USA · School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN 47907, USA
When (and How) to Trust the Expert: Diagnosing Query-Time Expert-Guided Reinforcement Learning
May 9, 2026Yann Berthelot, Philippe Preux, Riad AkrourRL Control RL Benchmarks
UMR 9189 – CRIStAL · CNRS, Inria, Centrale Lille · Saint-Gobain Research Paris +3
Generative Actor-Critic with Soft Bridge Policies
May 9, 2026Ke He, Le He, Shunpu Tang +2Policy Optimization Maximum Entropy RL
Guangzhou University · Zhejiang University · Southeast University
Bi-Level Reinforcement Learning Control for an Underactuated Blimp via Center-of-Mass Reconfiguration
May 2, 2026Xiaorui Wang, Hongwu Wang, Yue Fan +2RL Control Aerial Robotics
SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control
May 1, 2026Stavros Orfanoudakis, Pedro P. VergaraRepresentation Learning Policy Optimization
Delft University of Technology, The Netherlands
Multi-action Tangled Program Graphs for Multi-task Reinforcement Learning with Continuous Control
Apr 28, 2026Quentin Vacher, Nicolas Beuve, Mickaël Dardaillon +1RL Benchmarks Genetic Programming
IETR · Univ Rennes, INSA Rennes, CNRS, IETR – UMR 6164, F-35000 Rennes, France
Mean Flow Policy Optimization
Apr 16, 2026Xiaoyi Dong, Xi Sheryl Zhang, Jian ChengMeanFlow Mean Flow
C2DL, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · AiRiA +1

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

FERPO: Forward Entropy-Regularized Policy Optimization

Sebastian Sanokowski, Alireza Sarmadi, Majid Khadiv

Applied and Theoretical Aspects of Robot Intelligence (ATARI) Lab, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich

KL-Regularized RL Policy Optimization Maximum Entropy RL Continuous Control Policy Learning

Open paper AskPDF arXiv

Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically trained to predict returns, and accurate value predictions do not necessarily yield accurate action derivatives, potentially leading to unreliable policy updates. We propose Forward Entropy-Regularized Policy Optimization (FERPO), an on-policy maximum entropy reinforcement learning algorithm that performs policy improvement using critic values without differentiating the critic with respect to actions. FERPO derives an optimal target action distribution from a policy-improvement objective regularized by entropy and Kullback-Leibler (KL) divergence. We then fit the actor to this target by minimizing a forward-KL objective, estimated using self-normalized importance sampling (SNIS) with actions drawn from the rollout policy. By limiting the target distribution's deviation from the rollout policy, the KL regularization helps keep these importance weights well behaved. In contrast to reverse-KL objectives, which can favor a subset of the target distribution's modes, the forward-KL objective encourages coverage of multiple high-value modes and thereby promotes exploration. Experiments and ablations on MuJoCo Playground and ManiSkill show competitive performance and sample-efficiency gains. Computational benchmarks also demonstrate faster actor updates than Relative Entropy Pathwise Policy Optimization (REPPO).

Momentum

Related topics

Latest papers 34