Lionel Briand
Papers
5
Total Citations
64
H-Index
3
About
Lionel Briand is a prominent software engineering researcher whose work sits at the critical intersection of artificial intelligence safety, search-based testing, and deep learning verification. His research focuses primarily on ensuring the reliability and safety of Deep Reinforcement Learning (DRL) systems deployed in high-stakes environments such as autonomous driving, robotics, and healthcare — domains where algorithmic failures can carry severe real-world consequences. Briand's most influential contribution, "A Search-Based Testing Approach for Deep Reinforcement Learning Agents," has garnered 46 citations since 2023, establishing him as a leading voice in DRL testing methodology. His SMARLA framework further advances this agenda by providing runtime safety monitoring for DRL agents, addressing a critical gap in deployment-ready AI systems. More recently, his work on GAN-enhanced simulations for DNN testing and retraining demonstrates his commitment to pushing the boundaries of automated test generation for neural networks. What distinguishes Briand's research is its practical urgency — rather than theoretical exploration alone, his methods directly tackle the challenge of making AI trustworthy in safety-critical applications. His sustained focus on search-based and automated testing approaches makes his work essential reading for researchers and engineers working on responsible AI deployment.
Research Focus
Key Achievements
Top Papers
- 1A Search-Based Testing Approach for Deep Reinforcement Learning Agents46 citations · 2023
- 2
- 3A Search-Based Testing Approach for Deep Reinforcement Learning Agents7 citations · 2022
- 4Search-Based DNN Testing and Retraining With GAN-Enhanced Simulations2 citations · 2025
- 5