RL Control

RL: Reinforcement Learning

Follow this topic Ask about this topic

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

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

May 7, 2026

Soft Deterministic Policy Gradient with Gaussian Smoothing

Deterministic policy gradient (DPG) is widely utilized for continuous control; however, it inherently relies on the differentiability of the critic with respect to the action during policy updates. This assumption is violated in practical control problems involving sparse or discrete rewards, leading to ill-defined policy gradients and unstable learning. To address these challenges, we propose a principled alternative based on a smoothed Bellman equation formulated via Gaussian smoothing. Specifically, we define a novel action-value function based on a smoothed Bellman equation and derive the soft deterministic policy gradient (Soft-DPG). Our formulation eliminates explicit dependence on critic action-gradients and ensures that the gradient remains well-defined even for non-smooth Q-functions. We instantiate this framework into a deep reinforcement learning algorithm, which we call soft deep deterministic policy gradient (Soft DDPG). Empirical evaluations on standard continuous control benchmarks and their discretized-reward variants show that Soft DDPG remains competitive in dense-reward settings and provides clear gains in most discretized-reward environments, where standard DDPG is more sensitive to irregular critic landscapes.

Hyunjun Na, Donghwan Lee

School of Electrical Engineering, KAIST 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea

RL Control Policy Gradient Policy Gradient Methods Sparse-Reward RL Deep Deterministic Policy Gradient

May 7, 2026

Offline Reinforcement Learning for Rotation Profile Control in Tokamaks

Tokamaks remain leading candidates for achieving practical fusion energy, yet many important control problems inside these devices are still difficult or unsolved. One such challenge is controlling the plasma rotation profile, which strongly influences stability, confinement, and transport. While the average rotation can be controlled, controlling the full profile is challenging due to high dimensionality, response to multiple actuators and dependence on plasma condition. Learning-based control methods, such as reinforcement learning (RL), provide a potential solution to this challenging problem with ability to model complex interactions leading to effective multi-input multi-output control. However, learning such policies is challenging due to the lack of accurate simulators that can model the rotation profile dynamics. In this work, we investigate the use of offline RL and offline model-based RL algorithms for rotation profile control, training them solely on historical data from the DIII-D tokamak. Our final method uses probabilistic models of plasma dynamics to generate rollouts for RL training. We deploy this policy on the DIII-D Tokamak and observe promising real-world results. We conclude by highlighting key challenges and insights from training and deploying an RL policy on a complex physical device while using only limited past data.

Rohit Sonker, Hiro Josep Farre Kaga, Jiayu Chen +5

1Robotics Institute, Carnegie Mellon University · 2Princeton University · 4The University of Hong Kong +2

RL Control Offline RL Feedback Control Model-Based RL

May 6, 2026

Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policies

A key capability of intelligent agents is to act effectively under incomplete state observations. Recurrent policies address this by compressing observation histories into a hidden state. In this work, we show that the hidden state of a recurrent policy admits a control-theoretic interpretation: it plays the role of the co-state in Pontryagin's minimum principle, and the readout that maps it to actions implements control-Hamiltonian minimization. The hidden state thus tracks the gradient of the value function, encoding the optimality structure of the underlying control problem. We formalize this correspondence through a class of policies we refer to as co-state policies (CPs) and show that several modern recurrent cells implicitly realize this structure. The correspondence also allows for a co-state loss for actor-critic training, in which the critic's gradient serves as a target for the actor's hidden state. Empirically, we find that hidden states trained with the co-state loss encode co-state information beyond what is linearly decodable from the environment state alone, and that the loss improves policies both within and outside this class on challenging locomotion tasks, including the H1 and Berkeley humanoids. By connecting the minimum principle to recurrent memory, we provide a control-theoretic account of what hidden states compute in continuous control and a mechanism for shaping them toward optimality.

David Leeftink, Max Hinne, Marcel van Gerven

Department of Machine Learning and Neural Computating Donders Institute for Brain, Cognition and Behaviour Radboud University, Nijmegen, the Netherlands.

RL Control Reinforcement Learning Partially Observable RL Policy Learning Optimal Control

May 6, 2026

Worst-Case Discovery and Runtime Protection for RL-Based Network Controllers

RL-based controllers achieve strong average-case performance in networking tasks such as congestion control and adaptive bitrate streaming. Yet their performance can degrade severely under network conditions where strong performance is still achievable. Identifying such conditions and quantifying the resulting performance gap is intractable by enumeration, while the sequential and closed-loop nature of RL controllers makes formal verification methods impractical. We present ReGuard, a framework that discovers worst-case scenarios for a given RL controller and protects it against them at inference time without retraining. Discovery is formulated as a bilevel regret-maximization problem, which yields a certified lower bound on the worst-case performance gap. The discovered trajectories are then analyzed as counterfactuals and compiled into lightweight logic rules that intervene only when a risky state is detected, leaving the controller's behavior unchanged otherwise. We evaluate ReGuard across three RL-based network controllers: Pensieve, Sage, and Park. ReGuard discovers scenarios in which the controller's performance is 43

-

64% worse than what is achievable. ReGuard not only discovers gaps 57% to 6

\times

larger than those found by the strongest baselines but also shrinks them by 79

-

85% via lightweight rule-based protection while preserving nominal performance. ReGuard's protection extends beyond the scenarios it discovers, improving performance across a wider range of network conditions.

Hongyu Hè, Minhao Jin, Maria Apostolaki

Princeton

RL Control Safe RL Robust RL

May 4, 2026

Sim-to-Real Transfer and Robustness Evaluation of Reinforcement Learning Control with Integrated Perception on an ASV for Floating Waste Capture

Autonomous surface vessels for floating-waste removal operate under varying hydrodynamics, external disturbances, and challenging water-surface perception. We present a field-validated system that combines camera-based polarimetric perception with a lightweight DRL-based controller for floating-waste detection and capture. Camera detections are converted into water-surface target points and tracked by a controller trained entirely in simulation and deployed directly on a retrofitted ASV platform. Our main contribution is a sim-to-real testing methodology that combines a two-stage simulation protocol with a perception abstraction module designed to mimic real camera behavior, enabling reproducible field trials and explicit evaluation of the sim-to-real gap. We apply this framework in matched simulation and field experiments across 14 disturbance regimes to expose failure modes and evaluate robustness. The results show centimeter-level terminal accuracy and indicate robust control performance under the evaluated perturbation regimes. The main source of degradation is insufficient actuation-model fidelity. We also demonstrate the system in a search-and-capture application using real camera detections in real-world conditions over areas of up to

450~m^2

. The study distills practical lessons for reliable transfer, including improved actuation-model fidelity, targeted domain randomization, and careful management of latency and timestamps across modules, while highlighting remaining challenges.

Luis F. W. Batista, Stéphanie Aravecchia, Cédric Pradalier

GeorgiaTech Europe - IRL2958 GT-CNRS, Metz, France

RL Control Sim-to-Real Transfer

May 4, 2026

Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based Adaptation

Closed-loop management of geological CO2 storage requires control policies that adapt to uncertain reservoir behavior while relying on observations that are realistically available during operation. This work formulates CO2 injection and brine-production control as a partially observable sequential decision problem and studies deployable deep reinforcement-learning controllers trained with high-fidelity reservoir simulation. We first compare privileged-state, well-only, history-conditioned, masking-curriculum, and asymmetric teacher-student model-free policies in order to quantify the value of temporal well-response information and training-time privileged simulator states. We then evaluate a latent model-based adaptation pipeline that reuses nominal latent dynamics and retunes controllers under known injector failure, leakage-induced dynamics and reward shift, and compartmentalized reservoir connectivity. The results show that history-conditioned policies recover nearly all of the privileged-state performance while using only deployable well-level information, and that latent model-based retuning outperforms direct model-free retuning under the same scenario-specific real-simulator budget in the abnormal operating cases. The proposed framework therefore provides a simulator-budget-aware alternative to repeated online history matching and re-optimization for closed-loop CO2 storage control.

Sofianos Panagiotis Fotias, Vassilis Gaganis

School of Mining and Metallurgical Engineering, National Technical University of Athens, Athens 157 73, Greece · Institute of Geoenergy, Foundation for Research and Technology, Chania, 73100, Greece

RL Control Latent Dynamics Modeling Partially Observable RL Model-Based RL

May 4, 2026

Reinforcement Learning Trained Observer Control for Bearings-Only Tracking

This paper develops a deep reinforcement learning based observer control policy for autonomous bearings-only tracking of a moving target. The observer manoeuvre problem is formulated as a belief Markov decision process, where the belief state is represented by the posterior of a cubature Kalman filter (CKF). The reward function is designed to address two conflicting objectives: minimising the absolute target position estimation error (Euclidean distance) and maintaining CKF estimation consistency (Mahalanobis distance). The reward is formulated as a geometric interpolation between the two objectives on the Pareto front, parametrised by a weighting factor

β\in [0,1]

. The policy is implemented as a deep Q-network (DQN) trained over 50,000 episodes. Performance is evaluated over 5,000 Monte Carlo episodes and compared against two baselines: the perpendicular-to-bearing heuristic and the D-optimal Fisher information maximisation criterion. The results show that the DQN policy at

β= 0.7

achieves the best trade-off between accuracy and robustness: it matches the information-theoretic baseline on mean tracking accuracy while reducing the worst-case error by nearly a factor of ten, owing to the implicit filter-consistency regularisation provided by the Mahalanobis term in the reward.

Branko Ristic, Sanjeev Arulampalam

School of Engineering, RMIT University, Melbourne, VIC3000, Australia · Defence Science and Technology Group, Australia

May 3, 2026

Stability of Control Lyapunov Function Guided Reinforcement Learning

Reinforcement learning (RL) has become the de facto method for achieving locomotion on humanoid robots in practice, yet stability analysis of the corresponding control policies is lacking. Recent work has attempted to merge control theoretic ideas with reinforcement learning through control guided learning. A notable example of this is the use of a control Lyapunov function (CLF) to synthesize the reinforcement learning rewards, a technique known as CLF-RL, which has shown practical success. This paper investigates the stability properties of optimal controllers using CLF-RL with the goal of bridging experimentally observed stability with theoretical guarantees. The RL problem is viewed as an optimal control problem and exponential stability is proven in both continuous and discrete time using both core CLF reward terms and the additional terms used in practice. The theoretical bounds are numerically verified on systems such as the double integrator and cart-pole. Finally, the CLF guided rewards are implemented for a walking humanoid robot to generate stable periodic orbits.

Zachary Olkin, William D. Compton, Aaron D. Ames

The authors are with the Department of Control and Dynamical Systems at the California Institute of Technology.

RL Control Lyapunov Stability RL for Legged Locomotion Optimal Control RL Stability Control Lyapunov Functions

May 3, 2026

Remote Action Generation: Remote Control with Minimal Communication

We address the challenge of remote control where one or more actors, lacking direct reward access, are steered by a controller over a communication-constrained channel. The controller learns an optimal policy from observed rewards and communicates action guidance to the actors, which becomes demanding for large or continuous action spaces. To achieve rate-efficient communication throughout this interactive learning and control process, we introduce a novel framework leveraging remote generation. Instead of transmitting full action specifications, the controller sends minimal information, enabling the actors to locally generate actions by sampling from the controller's evolving target policy. This guided sampling is facilitated by an importance sampling approach. Concurrently, the actors use the received guidance as supervised learning data to learn the controller's policy. This actor-side learning improves their local sampling capabilities, progressively reducing future communication needs. Our solution, Guided Remote Action Sampling Policy (GRASP), demonstrates significant communication reduction, achieving an average 12-fold data reduction across all experiments (50-fold for continuous action spaces) compared to direct action transmission, and a 41-fold reduction compared to reward transmission.

Szymon Kobus, Deniz Gündüz

Electrical and Electronic Engineering Imperial College London

RL Control Reinforcement Learning Feedback Control

May 3, 2026

Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions

Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods struggle with the complexity and variability of the environment, reinforcement learning (RL) enables UAVs to learn adaptive behaviors through interaction with the environment. Existing research with RL prioritizes the mission success at the expense of mission time and safety of UAVs. This study integrates Potential Based Reward Shaping (PBRS) with Control Lyapunov Functions (CLF) and Control Barrier Functions (CBF) to simultaneously optimize mission time and ensure formal safety guarantees. An RL model is trained in a generalized simple environment, then used in complex scenarios incorporating a CLF-CBF-QP filter without further training. Experimental results in simulated environments demonstrate a significant reduction in mission time and outstanding performance in complex environment.

Ashik Abrar Naeem, Mohammad Ariful Haque

RL Control Control Lyapunov Functions UAV Navigation Safe Robot Navigation

May 2, 2026

Bi-Level Reinforcement Learning Control for an Underactuated Blimp via Center-of-Mass Reconfiguration

This paper investigates goal-directed tracking control of underactuated blimps with center-of-mass (CoM) reconfiguration. Unlike conventional overactuated blimp designs that rely on redundant actuation for simplified control, this paper focuses on a compact architecture consisting of two thrusters and a movable internal slider, aiming to improve energy efficiency and payload capacity. This hardware-efficient configuration introduces significant underactuation and strong nonlinear coupling between CoM dynamics and vehicle motion. To address these challenges, this paper proposes a bi-level reinforcement learning framework that explicitly decouples task-level CoM planning from continuous thrust control. The outer policy determines a target-dependent CoM configuration prior to flight, while the inner policy generates thrust commands to track straight-line references. To ensure stable learning, this paper introduces a two-stage learning strategy, supported by a convergence analysis of the resulting bi-level process. Extensive simulations and real-world experiments on a 27-goal evaluation set demonstrate that the proposed method consistently outperforms fixed-CoM baselines and PID-based controllers, achieving higher tracking accuracy, enhanced robustness, and reliable sim-to-real transfer.

Xiaorui Wang, Hongwu Wang, Yue Fan +2

RL Control Aerial Robotics Hierarchical RL Continuous Control

Apr 27, 2026

An Automatic Ground Collision Avoidance System with Reinforcement Learning

This article evaluates an artificial intelligence (AI)-based Automatic Ground Collision Avoidance System (AGCAS) designed for advanced jet trainers to enhance operational effectiveness. In the continuously evolving field of aerospace engineering, the integration of AI is crucial for advancing operations with improved timing constraints and efficiency. Our study explores the design process of an AI-driven AGCAS, specifically tailored for advanced jet trainers, focusing on addressing the AGCAS problem within a limited observation space. The system utilizes line-of-sight queries on a terrain server to ensure precise and efficient collision avoidance. This approach aims to significantly improve the safety and operational capabilities of advanced jet trainers.

Seyyid Osman Sevgili, Atahan Cilan, Mahir Demir +2

Turkish Aerospace Istanbul, Turkey

RL Control Collision Avoidance Aviation Safety

Apr 27, 2026

An Aircraft Upset Recovery System with Reinforcement Learning

This article explores the progress made in the creation of a pilot activated recovery system (PARS) for advanced jet trainers that utilizes artificial intelligence (AI) in an effort to enhance operational efficiency. The PARS model employs an advanced reinforcement learning (RL) architecture, incorporating a cutting-edge soft-actor critic (SAC) model and hyper-parameter optimization methods. Negative-g punishments and other handcrafted features remarked upon by control engineers and domain experts regarding PARS are also taken into account by the system. When evaluated by them, the AI model's behavior is deemed more desirable than that of conventional control methods.

Mahir Demir, Atahan Cilan, Seyyid Osman Sevgili +2

Turkish Aerospace Istanbul, Turkey

Apr 27, 2026

Perfecting Aircraft Maneuvers with Reinforcement Learning

This paper evaluates an advanced jet trainer's utilization of artificial intelligence (AI)-based aircraft aerobatic maneuvers with the intention of developing an AI-assisted pilot training module for specific aircraft maneuvers. A multitude of aircraft maneuvers have been simulated using reinforcement learning (RL) agents, which will serve as a training tool for future pilots.

Atahan Cilan, Mahir Demir, Özgün Can Yürütken +2

Turkish Aerospace Istanbul, Turkey

Apr 26, 2026

MUSIC: Learning Muscle-Driven Dexterous Hand Control

We present a data-driven approach for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform precise piano playing for novel pieces of music outside the reference dataset. Our approach combines high-frequency muscle-level control with low-frequency latent-space coordination in a hierarchical architecture. At the low level, general single-hand policies are trained via reinforcement learning to generate dynamic muscle-tendon activations while tracking trajectories from a large reference motion dataset. The resulting tracking policies are then distilled into variational autoencoder (VAE) models, yielding smooth and structured latent spaces that abstract away low-level muscle dynamics. For the high level, we train piece-specific policies to operate in this latent space, coordinating bimanual motions based on specific goals, denoted by note events extracted from given musical scores, to synthesize performances beyond the reference data. In addition, we present an enhanced musculoskeletal hand model that supports fine control of fingers for accurate low-level motion tracking and diverse high-level motion synthesis. We evaluate the control pipeline of our approach on a diverse piano repertoire spanning multiple musical styles and technical demands. Results demonstrate that our approach can synthesize coordinated bimanual motions with accurate key presses, and achieve the state-of-the-art performance of piano playing in physics-based dexterous control. We also show that our musculoskeletal hand model demonstrates superior biomechanical stability and tracking precision compared to the existing model, and validate that our musculoskeletal hand model and muscle-driven controller can generate physiologically plausible activation patterns that align with human electromyography (EMG) recordings.

Pei Xu, Yufei Ye, Shuchun Sun +3

Stanford University, USA · Clemson University, USA

Robotic Control RL Control Dexterous Manipulation

Apr 25, 2026

GIFT: Global stabilisation via Intrinsic Fine Tuning

Deep reinforcement learning policies achieve strong performance in complex continuous control environments with nonlinear contact forces. However, these policies often produce chaotic state dynamics, with trivially small changes to the initial conditions significantly impacting the long-term behaviour of the control system. This high sensitivity to initial conditions limits the application of Deep RL to real-world control systems where performance and stability guarantees are often required. To address this issue, we propose Global stabilisation via Intrinsic Fine Tuning (GIFT), a general-purpose training framework which directly optimises the global stability of existing high-performing deep RL policies using a custom reward function. We demonstrate that GIFT increase the stability of the control interaction while maintaining comparable task performance, thereby improving the suitability of deep RL policies for real-world control systems.

Rory Young, Nicolas Pugeault

School of Computing Science University of Glasgow

RL Control Reinforcement Learning RL Fine-Tuning Robust RL RL Stability

Apr 23, 2026

Insect-inspired modular architectures as inductive biases for reinforcement learning

Most reinforcement-learning (RL) controllers used in continuous control are architecturally centralized: observations are compressed into a single latent state from which both value estimates and actions are produced. Biological control systems are often organized differently. Insects, in particular, coordinate navigation, heading stabilization, memory, and context-dependent action selection through distributed circuits rather than a single monolithic controller. Motivated by this contrast, we study an RL policy architecture that decomposes control into interacting modules for sensory encoding, heading representation, sparse associative memory, recurrent command generation, and local motor control, with a learned arbitration mechanism that allocates motor authority across modules. The model is evaluated on a two-dimensional navigation task that require simultaneous food seeking, obstacle avoidance, and predator escape. In a six-seed predator-navigation experiment trained with Proximal Policy Optimization (PPO) for 75 updates, the modular policy achieves the strongest final mean performance among the tested controllers, with final episodic return

-2798.8\pm964.4

versus

-3778.0\pm628.1

for a centralized gated recurrent unit (GRU) and

-4727.5\pm772.5

for a centralized multilayer perceptron (MLP). The modular policy also attains the lowest final value loss and stable PPO optimization statistics while driving module-assignment entropy to

0.0457\pm0.0244

, indicating highly selective control allocation. These results suggest that distributed control can serve as a useful inductive bias for RL problems involving dynamically competing behavioral objectives.

Anne E. Staples

Department of Mechanical Engineering, Virginia Tech, Blacksburg, Virginia 24061, USA

RL Control Reinforcement Learning Policy Learning

Apr 22, 2026

A Systematic Review and Taxonomy of Reinforcement Learning-Model Predictive Control Integration for Linear Systems

The integration of Model Predictive Control (MPC) and Reinforcement Learning (RL) has emerged as a promising paradigm for constrained decision-making and adaptive control. MPC offers structured optimization, explicit constraint handling, and established stability tools, whereas RL provides data-driven adaptation and performance improvement in the presence of uncertainty and model mismatch. Despite the rapid growth of research on RL--MPC integration, the literature remains fragmented, particularly for control architectures built on linear or linearized predictive models. This paper presents a comprehensive Systematic Literature Review (SLR) of RL--MPC integrations for linear and linearized systems, covering peer-reviewed and formally indexed studies published until 2025. The reviewed studies are organized through a multi-dimensional taxonomy covering RL functional roles, RL algorithm classes, MPC formulations, cost-function structures, and application domains. In addition, a cross-dimensional synthesis is conducted to identify recurring design patterns and reported associations among these dimensions within the reviewed corpus. The review highlights methodological trends, commonly adopted integration strategies, and recurring practical challenges, including computational burden, sample efficiency, robustness, and closed-loop guarantees. The resulting synthesis provides a structured reference for researchers and practitioners seeking to design or analyze RL--MPC architectures based on linear or linearized predictive control formulations.

Mohsen Jalaeian Farimani, Roya Khalili Amirabadi, Davoud Nikkhouy +3

Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Milan, Italy · Department of Applied Mathematics, Ferdowsi University of Mashhad, Mashhad, Iran · Department of Applied Mathematics, Faculty of Mathematical Sciences, University of Guilan, Rasht, Iran +2

RL Control Model Predictive Control Feedback Control

Apr 21, 2026

Safe Continual Reinforcement Learning in Non-stationary Environments

Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments where system dynamics and operating conditions can change unexpectedly. Moreover, RL controllers acting in physical environments must satisfy safety constraints throughout their learning and execution phases, rendering transient violations during adaptation unacceptable. Although continual RL and safe RL have each addressed non-stationarity and safety, respectively, their intersection remains comparatively unexplored, motivating the study of safe continual RL algorithms that can adapt over the system's lifetime while preserving safety. In this work, we systematically investigate safe continual reinforcement learning by introducing three benchmark environments that capture safety-critical continual adaptation and by evaluating representative approaches from safe RL, continual RL, and their combinations. Our empirical results reveal a fundamental tension between maintaining safety constraints and preventing catastrophic forgetting under non-stationary dynamics, with existing methods generally failing to achieve both objectives simultaneously. To address this shortcoming, we examine regularization-based strategies that partially mitigate this trade-off and characterize their benefits and limitations. Finally, we outline key open challenges and research directions toward developing safe, resilient learning-based controllers capable of sustained autonomous operation in changing environments.

Austin Coursey, Abel Diaz-Gonzalez, Marcos Quinones-Grueiro +1

Institute for Software Integrated Systems, Vanderbilt University

RL Control Non-Stationary RL Safe RL

Apr 21, 2026

RL-ABC: Reinforcement Learning for Accelerator Beamline Control

Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We present RLABC (Reinforcement Learning for Accelerator Beamline Control), an open-source Python framework that automatically transforms standard Elegant beamline configurations into reinforcement learning environments. RLABC integrates with the widely-used Elegant beam dynamics simulation code via SDDS-based interfaces, enabling researchers to apply modern RL algorithms to beamline optimization with minimal RL-specific development. The main contribution is a general methodology for formulating beamline tuning as a Markov decision process: RLABC automatically preprocesses lattice files to insert diagnostic watch points before each tunable element, constructs a 57-dimensional state representation from beam statistics, covariance information, and aperture constraints, and provides a configurable reward function for transmission optimization. The framework supports multiple RL algorithms through Stable-Baselines3 compatibility and implements stage learning strategies for improved training efficiency. Validation on a test beamline derived from the VEPP-5 injection complex (37 control parameters across 11 quadrupoles and 4 dipoles) demonstrates that the framework successfully enables RL-based optimization, with a Deep Deterministic Policy Gradient agent achieving 70.3% particle transmission -- performance matching established methods such as differential evolution. The framework's stage learning capability allows decomposition of complex optimization problems into manageable subproblems, improving training efficiency. The complete framework, including configuration files and example notebooks, is available as open-source software to facilitate adoption and further research.

Anwar Ibrahim, Fedor Ratnikov, Maxim Kaledin +2

RL Control High-Energy Physics

Apr 17, 2026

Safe Deep Reinforcement Learning for Building Heating Control and Demand-side Flexibility

Buildings account for approximately 40% of global energy consumption, and with the growing share of intermittent renewable energy sources, enabling demand-side flexibility, particularly in heating, ventilation and air conditioning systems, is essential for grid stability and energy efficiency. This paper presents a safe deep reinforcement learning-based control framework to optimize building space heating while enabling demand-side flexibility provision for power system operators. A deep deterministic policy gradient algorithm is used as the core deep reinforcement learning method, enabling the controller to learn an optimal heating strategy through interaction with the building thermal model while maintaining occupant comfort, minimizing energy cost, and providing flexibility. To address safety concerns with reinforcement learning, particularly regarding compliance with flexibility requests, we propose a real-time adaptive safety-filter to ensure that the system operates within predefined constraints during demand-side flexibility provision. The proposed real-time adaptive safety filter guarantees full compliance with flexibility requests from system operators and improves energy and cost efficiency -- achieving up to 50% savings compared to a rule-based controller -- while outperforming a standalone deep reinforcement learning-based controller in energy and cost metrics, with only a slight increase in comfort temperature violations.

Colin Jüni, Mina Montazeri, Yi Guo +3

Urban Energy Systems Laboratory, Swiss Federal Laboratories for Materials Science and Technology, Dubendorf, Switzerland. · School of Automation, Beijing Institute of Technology, Haidian District, Beijing, China · Reliability and Risk Engineering Laboratory, ETH Zürich, CH-8092, Switzerland.

RL Control Building Energy Management Demand Response Feedback Control Safe RL Heating, Ventilation, and Air Conditioning Control

Apr 15, 2026

Timescale Separation Enables Deep Reinforcement Learning Control of Rotating Detonation Engine Mode Transitions

Rotating detonation engines (RDEs) are a promising propulsion concept that may offer higher thermodynamic efficiency and specific impulse than conventional systems, but nonlinear phenomena, including transitions to oscillatory or chaotic propagation modes, can hinder practical operation. Deep Reinforcement Learning (DRL) has emerged as a promising method for controlling complex nonlinear dynamics such as those observed in RDEs. However, the multi-timescale nature of the RDE system makes direct application of DRL challenging. We address this challenge by reformulating the DRL problem in a moving reference frame that follows the detonation-wave pattern, making the wave structure appear quasi-steady to the agent. This reformulation enables scale separation between fast detonation propagation and slower operating-mode dynamics. We train DRL controllers to modulate spatially segmented injection pressure in a one-dimensional reduced-order RDE model and induce rapid transitions between different mode-locked states. Across a range of actuation periods, initial states, and target modes, controllers trained in the moving frame learn more reliably than those trained in a stationary frame and remain effective over a broader range of actuation periods. These results suggest that symmetry-aware moving reference frame formulations may be useful for related multiscale flow-control problems and that scale separation should be exploited whenever possible to enable DRL control of multi-timescale systems.

Kristian Holme, Jean Rabault, Ricardo Vinuesa +1

University of Oslo · Independent Researcher, Oslo · University of Michigan

Apr 14, 2026

Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring

Although autonomous underwater vehicles promise the capability of marine ecosystem monitoring, their deployment is fundamentally limited by the difficulty of controlling vehicles under highly uncertain and non-stationary underwater dynamics. To address these challenges, we employ a data-driven reinforcement learning approach to compensate for unknown dynamics and task variations. Traditional single-task reinforcement learning has a tendency to overfit the training environment, thus, limit the long-term usefulness of the learnt policy. Hence, we propose to use a contextual multi-task reinforcement learning paradigm instead, allowing us to learn controllers that can be reused for various tasks, e.g., detecting oysters in one reef and detecting corals in another. We evaluate whether contextual multi-task reinforcement learning can efficiently learn robust and generalisable control policies for autonomous underwater reef monitoring. We train a single context-dependent policy that is able to solve multiple related monitoring tasks in a simulated reef environment in HoloOcean. In our experiments, we empirically evaluate the contextual policies regarding sample-efficiency, zero-shot generalisation to unseen tasks, and robustness to varying water currents. By utilising multi-task reinforcement learning, we aim to improve the training effectiveness, as well as the reusability of learnt policies to take a step towards more sustainable procedures in autonomous reef monitoring.

Melvin Laux, Yi-Ling Liu, Rina Alo +4

Robotics Research Group, University of Bremen, Bremen, Germany · Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany

RL Control Underwater Robotics Multi-Task RL Robust RL

Apr 14, 2026

A Comparison of Reinforcement Learning and Optimal Control Methods for Path Planning

Path-planning for autonomous vehicles in threat-laden environments is a fundamental challenge. While traditional optimal control methods can find ideal paths, the computational time is often too slow for real-time decision-making. To solve this challenge, we propose a method based on Deep Deterministic Policy Gradient (DDPG) and model the threat as a simple, circular no-go' zone. A mission failure is claimed if the vehicle enters this no-go' zone at any time or does not reach a neighborhood of the destination. The DDPG agent is trained to learn a direct mapping from its current state (position and velocity) to a series of feasible actions that guide the agent to safely reach its goal. A reward function and two neural networks, critic and actor, are used to describe the environment and guide the control efforts. The DDPG trains the agent to find the largest possible set of starting points (

feasible set'') wherein a safe path to the goal is guaranteed. This provides critical information for mission planning, showing beforehand whether a task is achievable from a given starting point, assisting pre-mission planning activities. The approach is validated in simulation. A comparison between the DDPG method and a traditional optimal control (pseudo-spectral) method is carried out. The results show that the learning-based agent may produce effective paths while being significantly faster, making it a better fit for real-time applications. However, there are areas (

infeasible set'') where the DDPG agent cannot find paths to the destination, and the paths in the feasible set may not be optimal. These preliminary results guide our future research: (1) improve the reward function to enlarge the DDPG feasible set, (2) examine the feasible set obtained by the pseudo-spectral method, and (3) investigate the arc-search IPM method for the path planning problem.

Qiang Le, Yaguang Yang, Isaac E. Weintraub

Department of Electrical and Computer Engineering, Hampton University Hampton, USA · Air Warfare Directorate, Air Force Research Laboratory Wright-Patterson, USA

Safe Motion Planning Autonomous Driving Planning RL Control Optimal Control

Apr 13, 2026

Hierarchical RL-MPC Control for Dynamic Wake Steering in Wind Farms

Wind farm wake steering optimization is challenging due to complex flow physics and changing conditions. This paper presents a hierarchical framework that combines reinforcement learning with model predictive control, where an RL agent learns compensatory state estimates for an MPC controller, rather than directly controlling turbines. Evaluated on a three-turbine case, the approach achieves a 23% power gain over the baseline control and surpasses the idealized MPC with perfect state knowledge. Compared to direct RL control, the hybrid architecture maintains superior safety characteristics during training while achieving comparable performance with more stable control actions.

Marcus Binder Nilsen, Teodor Olof Benedict Åstrand, Tuhfe Göçmen +1

Technical University of Denmark, Department of Wind and Energy Systems. Roskilde, Frederiksborgvej 399, Denmark

RL Control Model Predictive Control Hierarchical RL

Apr 13, 2026

Accelerating Reinforcement Learning for Wind Farm Control via Expert Demonstrations

Reinforcement learning (RL) offers a promising approach for adaptive wind farm flow control, yet its practical deployment is hindered by slow training convergence and poor initial performance, factors that could translate to years of reduced power output if an untrained agent were deployed directly. This work investigates whether domain knowledge from steady-state wake models can accelerate RL training and improve initial controller performance. We propose a pretraining methodology in which expert demonstrations are generated by deploying a PyWake-based steady-state optimizer within a dynamic wake simulation (WindGym), then used to initialize both the actor and critic networks of a Soft Actor-Critic agent via behavior cloning. Experiments on a 2x2 wind farm show that pretraining eliminates the costly initial learning phase: while an untrained agent underperforms the greedy zero-yaw baseline by approximately 12%, pretraining raises initial performance to near-baseline levels. During online fine-tuning, all configurations converge within 250,000 environment steps to achieve similar performance, ultimately exceeding that of a lookup-table controller, which reaches approximately 7% power gain after 500,000 steps.

Marcus Binder Nilsen, Julian Quick, Tuhfe Göçmen +2

Department of Wind and Energy Systems, Technical University of Denmark, Roskilde, Denmark

RL Control Offline-To-Online RL Power Systems

Apr 13, 2026

ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching

Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins recent large-scale embodied AI systems. However, FM policies trained via imitation learning inherit the limitations of demonstration data; surpassing suboptimal behaviors requires reinforcement learning (RL) fine-tuning. Recent methods convert deterministic flows into stochastic differential equations (SDEs) with learnable noise injection, enabling exploration and tractable likelihoods, but such noise-only control can compromise training efficiency when demonstrations already provide strong priors. We observe that modulating the drift via the score function, i.e., the gradient of log-density, steers exploration toward high-probability regions, improving stability. The score admits a closed-form expression from the velocity field, requiring no auxiliary networks. Based on this, we propose ScoRe-Flow, a score-based RL fine-tuning method that combines drift modulation with learned variance prediction to achieve decoupled control over the mean and variance of stochastic transitions. Experiments demonstrate that ScoRe-Flow achieves 2.4x faster convergence than flow-based SOTA on D4RL locomotion tasks and up to 5.4% higher success rates on Robomimic and Franka Kitchen manipulation tasks.

Xiaotian Qiu, Lukai Chen, Jinhao Li +3

Zhejiang University, Hangzhou, China · Shanghai Innovation Institute · Shanghai Jiao Tong University, Shanghai, China +1

RL for Flow Matching Models Flow-Based Policy Learning RL Control Robotic RL Reinforcement Learning RL for Generative Models

Apr 10, 2026

Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing

Autonomous racing without prebuilt maps is a grand challenge for embedded robotics that requires kinodynamic planning from instantaneous sensor data at the acceleration and tire friction limits. Out-Of-Distribution (OOD) generalization to various racetrack configurations utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control, with implicit localization. These comprise Behavioral Cloning (BC) that is capped to human reaction times and Deep Reinforcement Learning (DRL) which requires large-scale collisions for comprehensive training that can be infeasible without simulation but is arduous to transfer to reality, thus exhibiting greater performance than BC in simulation, but actuation instability on hardware. This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN) that utilizes less than 1% of the computation of BC and model-based DRL. Slaloming from simulation to reality transfer and variance-induced conservatism are eliminated with the combination of a physics engine exploit-aware reward and the replacement of an explicit collision penalty with an implicit truncation of the value horizon. The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model. System identification illuminates a functional bifurcation where the first layer compresses spatial observations to extract digitized track features with higher resolution in corner apexes, and the second encodes nonlinear dynamics.

Shathushan Sivashangaran, Apoorva Khairnar, Sepideh Gohari +2

Autonomous Robots and Vehicles Laboratory, College of Engineering, Virginia Commonwealth University, Richmond, VA 23284, USA. · Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA 24061, USA. · Robotics Department, University of Michigan, Ann Arbor, MI 48109, USA.

Autonomous Racing RL Control Physics-Informed RL Robot Dynamics Learning

Apr 10, 2026

Physics-guided surrogate learning enables zero-shot control of turbulent wings

Turbulent boundary layers over aerodynamic surfaces are a major source of aircraft drag, yet their control remains challenging due to multiscale dynamics and spatial variability, particularly under adverse pressure gradients. Reinforcement learning has outperformed state-of-the-art strategies in canonical flows, but its application to realistic geometries is limited by computational cost and transferability. Here we show that these limitations can be overcome by exploiting local structures of wall-bounded turbulence. Policies are trained in turbulent channel flows matched to wing boundary-layer statistics and deployed directly onto a NACA4412 wing section at

Re_c=2\times10^5

without additional training on the wing, constituting zero-shot deployment. The transferred policies reduce total drag by 11.1%, while state-of-the-art opposition control reduces it by 8.9%. With the actuation cost taken into account, the corresponding net-energy savings are 10.9% and 8.8%, respectively. Surrogate training provides an estimated improvement of four orders of magnitude in exploration efficiency over direct on-wing training, enabling scalable flow control.

Yuning Wang, Pol Suarez, Mathis Bode +1

Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI 48109, USA. · FLOW, Engineering Mechanics, KTH Royal Institute of Technology, SE-100 44 Stockholm, Sweden. · Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, 52425 Jülich, Germany

RL Control Computational Fluid Dynamics Zero-Shot Learning

Apr 10, 2026

Musculoskeletal Motion Imitation for Learning Personalized Exoskeleton Control Policy in Impaired Gait

Designing generalizable control policies for lower-limb exoskeletons remains fundamentally constrained by exhaustive data collection or iterative optimization procedures, which limit accessibility to clinical populations. To address this challenge, we introduce a device-agnostic framework that combines physiologically plausible musculoskeletal simulation with reinforcement learning to enable scalable personalized exoskeleton assistance for both able-bodied and clinical populations. Our control policies not only generate physiologically plausible locomotion dynamics but also capture clinically observed compensatory strategies under targeted muscular deficits, providing a unified computational model of both healthy and pathological gait. Without task-specific tuning, the resulting exoskeleton control policies produce assistive torque profiles at the hip and ankle that align with state-of-the-art profiles validated in human experiments, while consistently reducing metabolic cost across walking speeds. For simulated impaired-gait models, the learned control policies yield asymmetric, deficit-specific exoskeleton assistance that improves both energetic efficiency and bilateral kinematic symmetry without explicit prescription of the target gait pattern. These results demonstrate that physiologically plausible musculoskeletal simulation via reinforcement learning can serve as a scalable foundation for personalized exoskeleton control across both able-bodied and clinical populations, eliminating the need for extensive physical trials.

Itak Choi, Ilseung Park, Eni Halilaj +1

Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213 USA.

Hip Exoskeleton Control Assistive Robotics Ankle Exoskeleton Control RL Control