Mojtaba Bagherzadeh
Papers
1
Total Citations
7
H-Index
1
About
Mojtaba Bagherzadeh is a researcher specializing in software testing, artificial intelligence, and the reliability of deep learning systems, with a particular focus on ensuring the safety and robustness of intelligent autonomous agents. His most notable work, "A Search-Based Testing Approach for Deep Reinforcement Learning Agents" (2022), addresses one of the most pressing challenges in modern AI development: how to rigorously test deep reinforcement learning (DRL) systems before they are deployed in safety-critical environments such as autonomous driving and robotics. By applying search-based techniques to systematically explore the behavioral boundaries of DRL agents, Bagherzadeh's research offers a principled methodology for uncovering failure modes that traditional testing approaches often miss. This contribution is especially significant given the rapid adoption of DRL algorithms across high-stakes domains where system failures can have serious real-world consequences. With his work already accumulating citations within the research community, Bagherzadeh is establishing himself as a thoughtful contributor to the intersection of software engineering and AI safety — an area of growing urgency as autonomous systems become increasingly embedded in everyday life.
Research Focus
Key Achievements
Top Papers
- 1A Search-Based Testing Approach for Deep Reinforcement Learning Agents7 citations · 2022