I am a 2nd-year Ph.D. student and a Graduate Research Assistant at the Georgia Institute of Technology under the guidance of Dr. Suguman Bansal, working at the intersection of Formal Methods, Reinforcement Learning. My research is centered around the fusion of Formal Methods and Reinforcement Learning techniques, with growing interest in how LLMs can be leveraged to enhance decision-making, planning, and generalization in interactive learning environments. The overarching goal of my work is to create advanced AI systems that improve the scalability, robustness, and efficiency of RL algorithms. In essence, I aim to bridge the gap between Formal Methods, which provide rigorous mathematical guarantees and Reinforcement Learning, which excels in learning from interactions with the environment. By integrating these domains, including recent advances in LLMs, I aspire to develop AI solutions that are not only theoretically grounded and reliable, but also capable of generalizing across unseen scenarios, ultimately contributing to the development of more scalable and trustworthy autonomous agents.

During my undergraduate studies, I interned at Newcastle University in partnership with the Max Planck Institute, working under the supervision of Dr. Sadegh Soudjani and Dr. Arabinda Ghosh to develop Reinforcement Learning solutions for addressing challenges associated with stochastic max-plus linear systems.