RL Control

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 475% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 168

All topics

From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
Jun 2, 2026Saket Tiwari, Tejas Kotwal, George KonidarisRL Control Reinforcement Learning
Department of Computer Science Brown University · Department of Applied Mathematics Brown University
Extreme Motion Generation via Hybrid Null-Space Control for Straight-Line Path Following
Jun 2, 2026Xinyi Yuan, Weiwei Wan, Kensuke HaradaRobotic Control RL Control
Graduate School of Engineering Science, The University of Osaka, Japan.
Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildings
Jun 1, 2026Hallah Shahid Butt, Qiong Huang, Gökhan Demirel +6RL Control Reinforcement Learning
Karlsruhe Institute of Technology, 76344 Eggenstein-Leopoldshafen, Germany
Explainable deep reinforcement learning reveals energy-efficient control strategies for turbulent drag reduction
May 31, 2026Federica Tonti, Ricardo VinuesaRL Control Reinforcement Learning
Department of Aerospace Engineering University of Michigan Ann Arbor, MI 48109, United States
Interpretable Policy Distillation for Power Grid Topology Control
May 30, 2026Aleksandra Dmitruka, Karlis FreivaldsRL Control Reinforcement Learning
University of Latvia, Faculty of Exact Sciences and Technology, Riga, Latvia
The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems
May 29, 2026Tobias Lademann, Théo Vincent, Jan Peters +1RL Control Partially Observable RL
Institute for Production Management, Technology and Machine Tools (PTW), Technical University of Darmstadt · DFKI GmbH, SAIROL · Department of Computer Science, Technical University of Darmstadt +1
FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
May 29, 2026Sungha Kim, Gawon Lee, Jusuk Lee +3RL Control Maximum Entropy RL
Seoul National University · Georgia Institute of Technology
ZAPS-DA: Zero-Phase Action Policy Smoothing with Decoupled Actor for Continuous Control in Reinforcement Learning
May 28, 2026Faiq ShamassRL Control Reinforcement Learning
San Diego, CA, USA
ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control
May 28, 2026Aoyu Pang, Maonan Wang, Yuejiao Xie +3RL Control Intelligent Transportation Systems
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China · Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong · Shanghai AI Laboratory, Shanghai, China +1
FedQHD: Closed-Form Function-Space Federated Reinforcement Learning
May 27, 2026Yuchen Hou, Yongshan Chen, Zhuowen Zou +4RL Control Federated Learning Aggregation
Northeastern University · University of California, Irvine · The George Washington University
Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks
May 26, 2026Lihui Liu, Mucun Sun, Caisheng WangRL Control Graph Neural Networks
Wayne State University, Detroit, MI, USA
Bayesian Deployment Approval for Learned Landing Controllers under Finite Rollout Validation
May 26, 2026Fei Jiang, Lei YangRL Control Reinforcement Learning
Independent Researcher, Seattle, WA, USA.
Adaptive Reinforcement Learning for Robust Open Quantum System Control: A Multi-Task Framework with Temporal Optimization
May 26, 2026Haftu W. Fentaw, Steve Campbell, Simon CatonRL Control Multi-Task RL
School of Computer Science, University College Dublin, Belfield, Dublin 4, Dublin, Ireland. · Centre for Quantum Engineering, Science, and Technology, University College Dublin, Belfield, Dublin 4, Dublin, Ireland. · School of Physics, University College Dublin, Belfield, Dublin 4, Dublin, Ireland.
When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control
May 26, 2026Guilin Zhang, Chuanyi Sun, Kai Zhao +3RL Control RL Benchmarks
The George Washington University, Washington, DC, USA
A perspective on fluid mechanical environments for challenges in reinforcement learning
May 24, 2026Shruti Mishra, Michael Chang, Vamsi Spandan +1RL Control Non-Stationary RL
Sony AI · Cohere Labs Community · The Hebrew University of Jerusalem
Emission-Aware Reinforcement Learning for Sustainable Electric Vehicle Charging and Carbon Dioxide Reduction Under Varying Renewable Penetration
May 23, 2026Ninglin Ou, Mohammad A. Razzaque, Iftekher Islam Shovon +5RL Control Multi-Objective Reinforcement Learning
anasc Research, School of Computer Science & IT, University College Cork, IE · School of Computing, Engineering and Digital Technologies, Teesside University, UK · International Energy Research Centre, Tyndall National Institute, Cork, IE +1
A Unified Python Framework for Direct PPO-based Control of AHUs with Economizer Logic and CO2-Constrained Ventilation
May 23, 2026Erfan Haghighat Damavandi, Davide Papurello, Mahdi Alibeigi +3RL Control Constrained RL
a Research and Development Department Owtana Tech- Turin, Italy · b Department of Energy Politecnico di Torino- Turin, Italy · c Department of Energy University of Tehran- Tehran, Iran +1
AcroRL: Learning Aggressive Quadrotor Inversion using Bidirectional Thrust
May 23, 2026Gabriel Rodriguez, Henri Sayag, Abhishek Rathod +4RL Control Aerial Robotics
Carnegie Mellon University · Shield AI
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
ACCoRD: Actor-Critic Conflict Resolution with Deep learning for O-RAN xApps
May 21, 2026Cezary Adamczyk, Adrian KliksRL Control Open Radio Access Network
Institute of Radiocommunications Poznan University of Technology Pozna´n, Poland · Lule˚a University of Technology Lule˚a, Sweden
Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
May 21, 2026Stefan Huber, Hannes Unger, Georg Schäfer +1RL Control Policy Optimization
Josef Ressel Centre for Intelligent and Secure Industrial Automation, University of Applied Sciences, Salzburg, Austria
DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning
May 20, 2026Bibek Poudel, Lei Zhu, Kevin Heaslip +2RL Control Intelligent Transportation Systems
University of Tennessee, Knoxville, TN, USA · University of North Carolina at Charlotte, Charlotte, NC, USA
Reinforcement Learning-based Control via Y-wise Affine Neural Networks: Comparative Case Studies for Chemical Processes
May 20, 2026Austin Braniff, Yuhe TianRL Control Feedback Control
Department of Chemical and Biomedical Engineering, West Virginia University, Morgantown, WV 26506 USA
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
Aerial Inspection Behaviors via RL-based Quadrotor Control for Under-canopy Forest Environments
May 19, 2026Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy +2RL Control Robot Trajectory Tracking
Robotics and AI group, in the Department of Computer Science, Electrical and Space Engineering at Luleåa University of Technology, Sweden
A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditions
May 18, 2026Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy +1RL Control Robot Trajectory Tracking
Robotics and AI group, in the Department of Computer Science, Electrical and Space Engineering at Luleåa University of Technology, Sweden
BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous control
May 15, 2026Yifan Zhang, Liang ZhengRL Control Non-Stationary RL
Central South University
Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
May 15, 2026Vishnu Saj, Sushil Vemuri, Dileep Kalathil +1RL Control Sim-to-Real Transfer
Texas A&M University College Station, TX, USA
Dynamic Plasma Shape Control with Arbitrary Sensor Subsets
May 15, 2026D. Sorokin, M. Stokolesov, A. Granovskiy +7RL Control Partially Observable RL
Next Step Fusion, Bertrange, L-8070, Luxembourg · Center for Energy Research, University of California San Diego, CA 92093, USA
Residual Reinforcement Learning for Robot Teleoperation under Stochastic Delays
May 14, 2026Kaize Deng, Zewen YangRobotic Control RL Control
Technical University of Munich, 80333 Munich, Germany

Jun 2, 2026, cs.LGJ/K move · Enter open · S save

From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments

Saket Tiwari, Tejas Kotwal, George Konidaris

Department of Computer Science Brown University · Department of Applied Mathematics Brown University

RL Control Reinforcement Learning Continuous-Time RL Actor-Critic Methods

Open paper AskPDF arXiv

We present a novel theoretical framework for deep reinforcement learning (RL) in continuous environments by modeling the problem as a continuous-time stochastic process, drawing on insights from stochastic control. Building on previous work, we introduce a viable model of actor-critic algorithm that incorporates both exploration and stochastic transitions. For single-hidden-layer neural networks, we show that the state of the environment can be formulated as a two time scale process: the environment time and the gradient time. Within this formulation, we characterize how the time-dependent random variables that represent the environment's state and estimate of the cumulative discounted return evolve over gradient steps in the infinite width limit of two-layer networks. Using the theory of stochastic differential equations, we derive, for the first time in continuous RL, an equation describing the infinitesimal change in the state distribution at each gradient step, under a vanishingly small learning rate. Overall, our work provides a novel nonparametric formulation for studying overparametrized neural actor-critic algorithms. We empirically corroborate our theoretical result using a toy continuous control task.

Momentum

Related topics

Latest papers 168