mlsanityData to 14 Oct 2026

Reinforcement learning in pursuit-evasion differential game: safety, stability and robustness

arXiv 2507.19516 ↗First posted 18 Jul 2025eess.SY cs.SYcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

Safety and stability are two critical concerns in pursuit-evasion (PE) problems in an obstacle-rich environment. Most existing works combine control barrier functions (CBFs) and reinforcement learning (RL) to provide an efficient and safe solution. However, they do not consider the presence of disturbances, such as wind gust and actuator fault, which may exist in many practical applications. This paper integrates CBFs and a sliding mode control (SMC) term into RL to simultaneously address safety, stability, and robustness to disturbances. However, this integration is significantly challenging due to the strong coupling between the CBF and SMC terms. Inspired by Stackelberg game, we handle the coupling issue by proposing a hierarchical design scheme where SMC and safe control terms interact with each other in a leader-follower manner. Specifically, the CBF controller, acting as the leader, enforces safety independently of the SMC design; while the SMC term, as the follower, is designed based on the CBF controller. We then formulate the PE problem as a zero-sum game and propose a safe robust RL framework to learn the min-max strategy online. A sufficient condition is provided under which the proposed algorithm remains effective even when constraints are conflicting. Simulation results demonstrate the effectiveness of the proposed safe robust RL framework.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 7 of its 35 references that are in the map. First posted on arXiv 18 Jul 2025.

Builds on

7 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Safe Learning Control with Optimality and Stability Guarantees26 Jan

Other references · 6

  1. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  2. 2021Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functionscited by 11
  3. 2020An Introduction to Pursuit-evasion Differential Gamescited by 9
  4. 2023Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Dronescited by 9
  5. 2015Efficient model-based reinforcement learning for approximate online optimalcited by 3
  6. 2021On the Undesired Equilibria Induced by Control Barrier Function Based Quadratic Programscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
  2. 2025A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions
  3. 2024Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning
  4. 2025Stability Enhancement in Reinforcement Learning via Adaptive Control Lyapunov Function
  5. 2026Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning
  6. 2025Safe model-based Reinforcement Learning via Model Predictive Control and Control Barrier Functions
  7. 2024Safe Reinforcement Learning Filter for Multicopter Collision-Free Tracking under disturbances
  8. 2025Multi-Constraint Safe Reinforcement Learning via Closed-form Solution for Log-Sum-Exp Approximation of Control Barrier Functions