Ranjan Sarkar
PhD Scholar, Artificial Intelligence
Indian Institute of Technology Kharagpur
I am a PhD Research Scholar in the Department of Artificial Intelligence (DoAI) at IIT Kharagpur, advised by Dr. Prabhat Kumar Mishra. I work at the RHPI Lab (Receding Horizon & Predictive Intelligence Lab). My research focuses on the intersection of Reinforcement Learning, Estimation, and Optimization, with applications in LLMs, Computer Vision, and Robotics.
Recent News
Preprint is available on arXiv.
Attended Workshop on AI for Science and Technology 2026 at IIT Kharagpur, supported by IndiaAI.
Delivered Self-Study Seminar on "An Estimation-Control duality and its extension to unknown distributions" . View Slides
Started working as a Research Scholar in RHPI Lab.
Research Interests
Machine Learning
Investigating the theoretical and probabilistic foundations of machine learning models to provide mathematical guarantees.
Reinforcement Learning
Focusing on the intersection of stochastic control and sequential decision-making to guarantee system stability and performance.
Stochastic Optimization
Developing scalable optimization frameworks and estimation techniques to handle high-dimensional uncertainty.
Publications
LQG solution for POMDP without estimating states: A minimum variance approach
Ranjan Sarkar, Prabhat K. Mishra
This work presents a minimum variance perspective to solve LQG-style POMDP problems without explicit state estimation.
Teaching Assistantship (TA)
Spring 2026
AI61006 • AI for Cyber Physical Systems
Instructor: Prof. Prabhat Kumar Mishra
View DetailsAutumn 2025
AI60211 • Algorithmic and Mathematical Foundations for AI
Instructor: Prof. Adway Mitra
View Details