Mohammad Wardat

About

Mohammad Wardat is a rising researcher at the intersection of software engineering and artificial intelligence, with a primary focus on the reliability and testing of deep reinforcement learning (RL) systems. His work addresses a critical challenge: as RL agents are deployed in high-stakes domains like autonomous driving and robotics, we need rigorous methods to ensure they are safe and robust. Wardat’s most cited paper, “μPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning Based on Real Faults” (2025, 4 citations), introduces a novel mutation testing framework specifically designed for RL. This pipeline uses real-world faults to systematically evaluate the adequacy of test suites for RL agents, moving beyond synthetic or random faults to more realistic failure scenarios. By pioneering mutation testing in this emerging field, Wardat provides practitioners with a practical tool to identify weaknesses in RL policies before deployment. His work is particularly notable for bridging the gap between traditional software testing and the unique challenges of sequential decision-making systems, marking him as a key contributor to the growing discipline of AI reliability engineering.

Research Focus

Key Achievements

Top Papers

1. 1
   $\mu \text{PRL}$: A Mutation Testing Pipeline for Deep Reinforcement Learning Based on Real Faults

   4 citations · 2025

Key Collaborators

Contact & Links