Constrained RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 175% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 143

All topics

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
Counterfactually Safe Reinforcement Learning
May 24, 2026Jingyi Li, Peng Wu, Chengchun ShiConstrained RL Safe RL
Department of Statistics and Data Science, National University of Singapore · School of Mathematics and Statistics, Beijing Technology and Business University · Department of Statistics, London School of Economics and Political Science
Reinforcement Learning with a Bilevel World-Model Architecture for Scan-Order Optimisation in Laser Directed Energy Deposition
May 24, 2026Xian Wu, Haoran Li, Yuanqi Chu +2Constrained RL
aCollege of Engineering, Design and Physical Sciences, Brunel University London, Uxbridge, UB8 3PH, United Kingdom · bThe State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
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
FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G
May 20, 2026Amin Farajzadeh, Melike Erol-KantarciFederated RL 6G Networks
School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada
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
Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
May 18, 2026Soheyl Massoudi, Gabriel Apaza, Milad Habibi +1RL for Code Generation LLM-Based Program Synthesis
ETH Zürich Zürich, Switzerland · University of Maryland College Park, MD, USA
parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning
May 15, 2026Yijun Lu, Zilei Yang, Yuyin MaReinforcement Learning Control Barrier Functions
Addressing Terminal Constraints in Data-Driven Demand Response Scheduling
May 14, 2026Maximilian Bloor, Martha White, Ehecatl Antonio del Rio Chanona +1Hierarchical RL Credit Assignment in RL
Sargent Centre for Process Systems Engineering, Imperial College London, London, SW7 2AZ, UK · Department of Computer Science, University of Alberta, Edmonton, AB, Canada · Department of Computing, Imperial College London, London, SW7 2AZ, UK
CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
May 14, 2026Zhenyang Ni, Yijiang Li, Ruochen Jiao +7Video Diffusion Models Reinforcement Learning
Northwestern University · University of California, San Diego · University of Oxford
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
May 13, 2026Qisong He, Xinmiao Huang, Jinwei Hu +4Constrained RL Risk-Sensitive RL
University of Liverpool, Liverpool, UK. · Universit´e Grenoble Alpes, Grenoble, France.
Learning Local Constraints for Reinforcement-Learned Content Generators
May 13, 2026Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis +1Constrained Generative Modeling Constrained RL
Institute of Digital Games, Msida, Malta · Game Innovation Lab, New York, New York, USA
Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints
May 13, 2026Timofey TomashevskiyNon-Stationary RL Reinforcement Learning
McMaster Centre for Software Certification Department of Computing and Software McMaster University, Canada
From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning
May 13, 2026Timofey TomashevskiyNon-Stationary RL Constrained RL
McMaster Centre for Software Certification Department of Computing and Software McMaster University, Canada
Optimal Policy Learning under Budget and Coverage Constraints
May 12, 2026Giovanni CerulliPolicy Optimization Combinatorial Optimization
CNR-IRCrES · National Research Council of Italy · Research Institute on Sustainable Economic Growth
Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning
May 12, 2026Jingduo Pan, Taoran Wu, Yiling Xue +1Constrained RL Safe RL
Key Laboratory of System Software (Chinese Academy of Sciences), Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China
Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
May 12, 2026Michael Lu, Max Qiushi Lin, Mo Chen +1Markov Decision Processes Last-Iterate Convergence
Simon Fraser University
Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
May 12, 2026Kihyun Yu, Beomhan Baek, Dabeen LeeRegret Minimization in RL Markov Decision Processes
1KAIST · 2Seoul National University
Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
May 12, 2026Kihyun Yu, Seoungbin Bae, Dabeen LeePrimal-Dual Optimization Markov Decision Processes
Department of Industrial and Systems Engineering KAIST · Department of Mathematical Sciences Seoul National University · Research Institute of Mathematics, Seoul National University; Interdisciplinary Program in Artificial Intelligence, Seoul National University; Korea Institute for Advanced Study
Beyond ESG Scores: Learning Dynamic Constraints for Sequential Portfolio Optimization
May 10, 2026Xin Li, Yan Ke, Longbing CaoConstrained RL Constrained Optimization
Macquarie University · The University of Queensland
Constraint-Aware Diffusion Priors for High-Fidelity and Versatile Quadruped Locomotion
May 9, 2026Jianhui Chen, Ruixin Zhan, Liu Liu +2Sim-to-Real Transfer Constrained RL
Amap, Alibaba Group
Multi-Objective Constraint Inference using Inverse reinforcement learning
May 7, 2026Syed Ihtesham Hussain Shah, Floris den Hengst, Aneta Lisowska +1Reinforcement Learning Constrained RL
Faculty of Sciences Vrije Universiteit Amsterdam
A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
May 7, 2026Hao YuPairwise Preference Learning LLM Alignment
Department of Automation, Tsinghua University
Constraint-Enhanced Reinforcement Learning Based on Dynamic Decoupled Spherical Radial Squashing
May 5, 2026Qijun Liao, Zhaoxin Yu, Jue YangRobotic Control Constrained RL
School of Mechanical Engineering, University of Science and Technology Beijing · Institute of Automation, Chinese Academy of Sciences
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
May 4, 2026Rufeng Chen, Zhaofan Zhang, Zhejiang Yang +2Diffusion-Based Planning Diffusion Guidance
1The Hong Kong University of Science and Technology (Guangzhou) · 2Jilin University
Experience Constrained Hierarchical Federated Reinforcement Learning for Large-scale UAV Teams in Hazardous Environments
May 4, 2026Qinwei Huang, Rui Zuo, Simon Khan +1Hierarchical Federated Learning Federated RL
EECS Syracuse University Syracuse, USA · AFRL Air Force Research Laboratory Rome, USA
Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning
May 1, 2026Jiaming Zhang, Yujie Yang, Yao Lyu +2Constrained RL Augmented Lagrangian Method
Global Optimality for Constrained Exploration via Penalty Regularization
Apr 30, 2026Florian Wolf, Ilyas Fatkhullin, Niao HeConstrained RL Maximum Entropy RL
The Computing & Mathematical Sciences Department, California Institute of Technology, Pasadena, CA. · Department of Computer Science, ETH Zurich, Switzerland. · 3ETH AI Center, ETH Zurich, Switzerland.
Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction
Apr 30, 2026Wentao Chen, Jingtang Chen, Mingjian Fu +4Reinforcement Learning UAV Navigation
Learning to Route Electric Trucks Under Operational Uncertainty
Apr 29, 2026Stavros Orfanoudakis, Ziyan Li, Ruixiao Yang +4Sequential Decision Making Electric Vehicle Charging
Delft University of Technology, Intelligent Electrical Power Grids, Delft, The Netherlands · Massachusetts Institute of Technology, Center of Transportation and Logistics, Cambridge, MA, United States of America · Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, Cambridge, MA, United States of America

May 26, 2026, cs.LGJ/K move · Enter open · S save

When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control

Guilin Zhang, Chuanyi Sun, Kai Zhao, Xu Chu+2

The George Washington University, Washington, DC, USA

RL Control RL Benchmarks Constrained RL Online Resource Allocation

Open paper AskPDF arXiv

A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help? We study this in RLScale-Bench, a reproducible benchmark and evaluation protocol for DRL on adaptive resource control, where an agent allocates compute to a dynamic workload under cost and service-level constraints. We evaluate PPO, DQN, A2C, SAC, TD3, and DDPG under matched architectures, training budgets, and reward functions against a calibrated rule-based baseline across six workload patterns and five seeds (240 runs), instantiate the benchmark on Kubernetes Horizontal Pod Autoscaling, and probe distribution-shift generalization. Three findings challenge common assumptions: (i) the calibrated controller achieves the lowest cost on all six workloads, though it trails the best RL agents on bursty and flash traffic; (ii) discrete-action algorithms outperform continuous-action ones by one to two orders of magnitude in constraint violations due to action-space mismatch; and (iii) no single algorithm dominates across workloads, with rankings shifting by up to four positions. The bottleneck in RL-based resource control is not algorithm selection but baseline calibration, reward engineering, and realistic evaluation protocols.

Momentum

Related topics

Latest papers 143