Follow the Updated Webpage!

About Me

I am a PhD Scholar in the Department of Artificial Intelligence (DoAI) at IIT Kharagpur, advised by Dr. Prabhat Kumar Mishra. I work at RHPI Lab (Receeding Horizon & Predictive Intelligence) on developing several algorithms of Reinforcement Learning and Control with theoretical foundations and practical use cases.

Research Interest

Theoretical Machine Learning, Optimization, Estimation
Reinforcement Learning, State-Space Models
Applied Linear Algebra, Stochastic Optimization & Control

Publications

LQG Solution for POMDP without estimating states: A minimum variance approach
Ranjan Sarkar, Prabhat K. Mishra
arXiv Preprint (Under Review), July 2026
DOI: https://doi.org/10.48550/arXiv.2607.12135

Recent Blogs

Gradient Descent Algorithm • Basics ExplainedExploring Exact Line Search Algorithm by visualizing its orthogonal successive search directions with animations.

Seminars

Tensor Seminar PPT.pdf

Tensor Decompositions for Model Reduction in CNN

MTP Tensor CP Decomposition.pdf

Tensor CP Decomposition in Image Processing (MTP)

Principal Component Analysis (PCA)

Data-driven Optimal Filtering for Linear System with unknown covariances
(Self-Study Seminar)

Get in touch at ranjan.sarkar.24@kgpian.iitkgp.ac.in

Page updated

Google Sites

Report abuse