My research is focused on finding the loopholes that give rise to specification gaming or reward hacking problems in AI systems. I am working on a mathematical logic framework where we can formalise multiple redundant causal paths contributing to such outcomes, and further, verify system safety.
The collaborative environment that STAI CDT provides is very helpful for my academic pursuits.
–
Pre-doctoral research: Computational Neuroscience, Florida Atlantic University.
Masters Qualification: Philosophy & Logic, ODTU/METU.
Google scholar: https://scholar.google.com/citations?user=LGUid5IAAAAJ&hl=en