mlsanityData to 7 Oct 2026

Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods

arXiv 2601.18142 ↗First posted 26 Jan 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Safe reinforcement learning (Safe RL) seeks to maximize rewards while satisfying safety constraints, typically addressed through Lagrangian-based methods. However, existing approaches, including PID and classical Lagrangian methods, suffer from oscillations and frequent safety violations due to parameter sensitivity and inherent phase lag. To address these limitations, we propose ADRC-Lagrangian methods that leverage Active Disturbance Rejection Control (ADRC) for enhanced robustness and reduced oscillations. Our unified framework encompasses classical and PID Lagrangian methods as special cases while significantly improving safety performance. Extensive experiments demonstrate that our approach reduces safety violations by up to 74%, constraint violation magnitudes by 89%, and average costs by 67%, establishing superior effectiveness for Safe RL in complex environments.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

26 of 51 references.

References · 26

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  4. 2015Continuous control with deep reinforcement learningcited by 3,279
  5. 2015Trust Region Policy Optimizationcited by 2,503
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  7. 2017Constrained Policy Optimizationcited by 928
  8. 2018Reward Constrained Policy Optimizationcited by 397
  9. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  10. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
  11. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  12. 2020Projection-Based Constrained Policy Optimizationcited by 195
14 more
  1. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learningcited by 153
  2. 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 140
  3. 2019IPO: Interior-point Policy Optimization under Constraintscited by 119
  4. 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 109
  5. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 76
  6. 2022Constrained Variational Policy Optimization for Safe Reinforcement Learningcited by 69
  7. 2022Constrained Update Projection Approach to Safe Policy Optimizationcited by 55
  8. 2022Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environmentscited by 54
  9. 2024Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulationcited by 21
  10. 2024DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancementcited by 11
  11. 2021Addressing Action Oscillations through Learning Policy Inertiacited by 8
  12. 2024MARLadona -- Towards Cooperative Team Play Using Multi-Agent Reinforcement Learningcited by 6
  13. 2024Adaptive Primal-Dual Method for Safe Reinforcement Learningcited by 4
  14. 2019A Parameter Formula Connecting PID and ADRCcited by 1

Built on by

Not cited yet.