English

Fault-Tolerant Design and Multi-Objective Model Checking for Real-Time Deep Reinforcement Learning Systems

Software Engineering 2026-03-25 v1

Abstract

Deep reinforcement learning (DRL) has emerged as a powerful paradigm for solving complex decision-making problems. However, DRL-based systems still face significant dependability challenges particularly in real-time environments due to the simulation-to-reality gap, out-of-distribution observations, and the critical impact of latency. Latency-induced faults, in particular, can lead to unsafe or unstable behaviour, yet existing fault-tolerance approaches to DRL systems lack formal methods to rigorously analyse and optimise performance and safety simultaneously in real-time settings. To address this, we propose a formal framework for designing and analysing real-time switching mechanisms between DRL agents and alternative controllers. Our approach leverages Timed Automata (TAs) for explicit switch logic design, which is then syntactically converted to a Markov Decision Process (MDP) for formal analysis. We develop a novel convex query technique for multi-objective model checking, enabling the optimisation of soft performance objectives while ensuring hard safety constraints for MDPs. Furthermore, we present MOPMC, a GPU-accelerated software tool implementing this technique, demonstrating superior scalability in both model size and objective numbers.

Keywords

Cite

@article{arxiv.2603.23113,
  title  = {Fault-Tolerant Design and Multi-Objective Model Checking for Real-Time Deep Reinforcement Learning Systems},
  author = {Guoxin Su and Thomas Robinson and Hoa Khanh Dam and Li Liu and David S. Rosenblum},
  journal= {arXiv preprint arXiv:2603.23113},
  year   = {2026}
}

Comments

To appear in ACM Transactions on Software Engineering and Methodology (TOSEM), 2026

R2 v1 2026-07-01T11:35:19.071Z