mlsanityData to 7 Oct 2026

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

arXiv 2602.20729 ↗First posted 24 Feb 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively avoiding min-max optimization. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 50 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

23 of 50 references.

References · 23

  1. 2017Robust Adversarial Reinforcement Learningcited by 439
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  3. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  4. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  5. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
  6. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  7. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
  8. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 135
  9. 2019Safe Reinforcement Learning Using Robust MPCcited by 72
  10. 2022Constrained Policy Optimization via Bayesian World Modelscited by 55
  11. 2022Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environmentscited by 54
  12. 2022Reachability Constrained Reinforcement Learningcited by 52
11 more
  1. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
  2. 2019Distributionally Robust Reinforcement Learningcited by 40
  3. 2022Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Riskcited by 40
  4. 2020Improving Robustness via Risk Averse Distributional Reinforcement Learningcited by 28
  5. 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithmscited by 27
  6. 2016Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policiescited by 19
  7. 2022CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learningcited by 16
  8. 2023Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learningcited by 12
  9. 2021Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPscited by 11
  10. 2023Safe Reinforcement Learning with Dual Robustnesscited by 10
  11. 2022Learning safety in model-based Reinforcement Learning using MPC and Gaussian Processescited by 3

Built on by

Not cited yet.