A Parametric Model for Near-Optimal Online Synthesis with Robust Reach-Avoid Guarantees
On the map: Deep reinforcement learning methods → Safe and constrained RL
Abstract (arXiv)
Objective: To obtain explainable guarantees in the online synthesis of optimal controllers for high-integrity cyber-physical systems, we re-investigate the use of exhaustive search as an alternative to reinforcement learning. Approach: We model an application scenario as a hybrid game automaton, enabling the synthesis of robustly correct and near-optimal controllers online without prior training. For modal synthesis, we employ discretised games solved via scope-adaptive and step-pre-shielded discrete dynamic programming. Evaluation: In a simulation-based experiment, we apply our approach to an autonomous aerial vehicle scenario. Contribution: We propose a parametric system model and a parametric online synthesis.
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 8 of its 22 references that are in the map. First posted on arXiv 1 Apr 2025.
Builds on
8 of 22 references.
References · 8
- 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
- 2020Explainability in Deep Reinforcement Learningcited by 97
- 2022Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environmentscited by 18
- 2016Formal Verification of Obstacle Avoidance and Navigation of Ground Robotscited by 2
- 2021Verified Synthesis of Optimal Safety Controllers for Human-Robot Collaborationcited by 2
- 2023Safe and Scalable Real-Time Trajectory Planning Framework for Urban Air Mobilitycited by 2
- 2023Layered controller synthesis for dynamic multi-agent systemscited by 1
- 2025Solvability of Approximate Reach-Avoid Gamescited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026SMC-ES: Automated synthesis of formally verified control policies
- 2025Control Synthesis with Reinforcement Learning: A Modeling Perspective
- 2025Safe and Near-Optimal Control with Online Dynamics Learning
- 2025The Crucial Role of Problem Formulation in Real-World Reinforcement Learning
- 2025Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning
- 2024Formal Synthesis of Controllers for Safety-Critical Autonomous Systems: Developments and Challenges
- 2025Fast Non-Episodic Adaptive Tuning of Robot Controllers with Online Policy Optimization
- 2026Towards Safe Reinforcement Learning with Reduced Conservativeness: A Case Study on Drone Flight Control