{"type":"ScholarlyArticle","title":"MSMAR-RL: Multi-Step Masked-Attention Recovery Reinforcement Learning for Safe Maneuver Decision in High-Speed Pursuit-Evasion Game","authors":[{"name":"Yang Zhao","slug":"yang-zhao","given":"Yang","family":"Zhao","affiliation":""},{"name":"Wenzhe Zhao","slug":"wenzhe-zhao","given":"Wenzhe","family":"Zhao","affiliation":""},{"name":"Xuelong Li","slug":"xuelong-li","given":"Xuelong","family":"Li","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/36","url":"https://ijcai.org/proceedings/2025/36","pdf":"https://ijcai.org/proceedings/2025/0036.pdf","markdown":"https://ijcai.org/proceedings/2025/36.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/36","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":36,"pages":{"first":311,"last":319},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}