Formal Methods for RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

13 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning
Oct 16, 2026Alexander W. Goodall, Francesco BelardinelliSafe RL Formal Methods for RL
Department of Computer Science Imperial College London
Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards
Oct 15, 2026Ruida Wang, Gerald Friedland, Tong Zhang +1Agentic RL RL for Tool Use
Amazon Web Services · University of Illinois Urbana-Champaign
HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
Jun 29, 2026Arshia Rafieioskouei, Tzu-Han Hsu, Matthew Lucas +1Formal Methods for RL Reinforcement Learning
Department of Computer Science and Engineering, Michigan State University, MI, USA.
Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation
Jun 17, 2026Ahmad Farooq, Kamran IqbalNeural Network Verification Formal Methods for RL
Department of Electrical and Computer Engineering, University of Arkansas at Little Rock, Little Rock, AR 72204 USA
Easy-to-Use Shielding for Reinforcement Learning
Jun 2, 2026Stefan Pranger, Bettina KönighoferFormal Methods for RL Reinforcement Learning
Institute of Information Security, Graz University of Technology
Certificate-Guided Evaluation of Reinforcement Learning Generalization
May 30, 2026Vignesh Subramanian, Đorđe Žikelić, Suguman BansalRL Benchmarks Formal Methods for RL
School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA · School of Computing and Information Systems, Singapore Management University, Singapore
Value Functions as Supermartingale Certificates
May 29, 2026Alessandro Abate, Daniel Contro, Mirco Giacobbe +2Formal Methods for RL Reinforcement Learning
University of Oxford, UK · University of Birmingham, UK
A Contractive Feedback Semantics for Reinforcement Learning
May 23, 2026Zuyuan ZhangFormal Methods for RL Reinforcement Learning
The George Washington University
COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
Mar 8, 2026Dennis GrossFormal Methods for RL Interpretability in RL
SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems
Feb 27, 2026Jialiang Fan, Weizhe Xu, Mengyu Liu +3Formal Methods for RL Large Language Model-Based Robot Planning
University of Notre Dame · Washington State University · University of Pennsylvania
Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments
Feb 27, 2026Florent DelgrangeFormal Methods for RL World Models
AI Lab, Vrije Universiteit Brussel & Flanders Make Brussels, Belgium
Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC
Feb 16, 2026Dennis GrossFormal Methods for RL Formal Verification
A Unified Framework for Zero-Shot Reinforcement Learning
Oct 23, 2025Jacopo Di Ventura, Jan Felix Kleuker, Aske Plaat +1Zero-Shot RL Formal Methods for RL
Leiden University

Oct 16, 2026J/K move · Enter open · S save

RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning

Alexander W. Goodall, Francesco Belardinelli

Department of Computer Science Imperial College London

Safe RL Formal Methods for RL Non-Markovian RL

Open paper AskPDF arXiv

In many real-world scenarios we need to consider formal requirements, such as safety and constraint compliance, to deploy Reinforcement Learning (RL) agents. In this paper we introduce RecReg, a safe RL framework capable of enforcing non-Markovian regular safety properties via recovery-based shielding. RecReg is a unified approach that supports different levels of a priori knowledge and safety guarantees. The paper primarily focuses on building the theoretical foundations for RecReg in the tabular setting, providing rigorous safety and convergence guarantees that are not present in related work. We provide an extensive set of empirical results using the MASA-Safe-RL library, and we outline an extension of RecReg to deep RL domains using SOTA model-based RL. Our empirical results demonstrate that RecReg achieves efficient learning and matches the theory in this paper.