---
title: "MSMAR-RL: Multi-Step Masked-Attention Recovery Reinforcement Learning for Safe Maneuver Decision in High-Speed Pursuit-Evasion Game"
authors:
  - "Yang Zhao"
  - "Wenzhe Zhao"
  - "Xuelong Li"
doi: "10.24963/ijcai.2025/36"
url: "https://ijcai.org/proceedings/2025/36"
pdf: "https://ijcai.org/proceedings/2025/0036.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "311-319"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Reinforcement learning"
  - "AI Ethics, Trust, Fairness: ETF: Safety and robustness"
  - "Robotics: ROB: Learning in robotics"
  - "Agent-based and Multi-agent Systems: MAS: Agent theories and models"
---

# MSMAR-RL: Multi-Step Masked-Attention Recovery Reinforcement Learning for Safe Maneuver Decision in High-Speed Pursuit-Evasion Game

Yang Zhao, Wenzhe Zhao, Xuelong Li

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 311-319. DOI: [10.24963/ijcai.2025/36](https://doi.org/10.24963/ijcai.2025/36)

## Abstract

Ensuring the safety of high-speed agent in dynamic adversarial environments, such as pursuit-evasion games with target-purchase and obstacle-avoidance, is a significant challenge. Existing reinforcement learning methods often fail to balance safety and reward under strict safety constraints and diverse environmental conditions. To address these limitations, this paper proposes a novel zero-constraint-violation recovery RL framework tailored for high-speed uav pursuit-evasion combat games. The framework includes three key innovations. (1) An extendable multi-step reach-avoid theory: we provide a zero-constraint-violation safety guarantee for multi-strategy reinforcement learning and enabling early danger detection in high speed game. (2) A masked-attention recovery strategy: we introduce a padding-mask attention architecture to handle spatiotemporal variations in dynamic obstacles with varying threat levels. (3) Experimental validation: we validate the framework in obstacle-rich pursuit-evasion scenarios, demonstrating its superiority through comparison with other algorithm and ablation studies. Our approach also shows potential for extension to other rapid-motion tasks and more complex hazardous scenarios.  Details and code could be found at https://msmar-rl.github.io.