Research

My research interests include a variety of topics within the field of artificial intelligence, including deep learning, Reinforcement Learning, Bayesian statistics, and autonomous systems. Specifically, I am interested in the development of self-driving cars, drones, smart grids, and Medical AI. I aim to make model behavior more explainable and increase awareness of predictive uncertainty. Additionally, I am exploring animal and human learning processes to pave the way for achieving artificial general intelligence.

Incorporating Generative Pre-trained Transformer (GPT) models into my research has been a significant development. This approach adds a dimension of natural language processing to reinforcement learning, and the ability of GPT models to understand and generate human-like text is remarkable. This integration can enhance the communication and interpretability of reinforcement learning models, and I am excited about its possibilities.

Keywords: Deep Reinforcement Learning, Deep Learning Neural Networks, Machine Learning, Transfer Learning, Actor-Critic, Software Development, Smart Grids, Gurobi Optimization Solver, Explainable AI, Contrastive Learning, GPT.

Journals Paper

1. Kundan Kumar, RaviKumar Gelli
   Physics-based Deep Reinforcement Learning for Grid-Resilient Volt-VAR Control Application
   IEEE Transactions on Smart Grid, 2023.
   Paper

Conferences Paper

1. Kundan Kumar, Gelli RaviKumar
   Transfer Learning Enhanced Deep Reinforcement Learning for Volt-Var Control in Smart Grids
   Conference of IEEE PES Grid Edge Technologies Conference & Exposition(Grid-edge), 2025.
   Paper Poster

2. Kundan Kumar,Aditya Akilesh Mantha, Gelli RaviKumar
   Bayesian Optimization for Deep Reinforcement Learning in Robust Volt-Var Control
   Conference on IEEE PES General Meeting(PES-GM), 2024.
   Paper Poster

3. Kundan Kumar, Gelli RaviKumar
   Deep RL-based Volt-VAR Control and Attack Resiliency for DER-integrated Distribution Grids
   Conference on IEEE Innovative Smart Grid Technologies(ISGT), 2024.
   Paper Poster

4. JK Francis, C Kumar, J Herrera-Gerena, Kundan Kumar, MJ Darr
   Deep Learning and Pattern-based Methodology for Multivariable Sensor Data Regression
   International Conference on Machine Learning (ICMLA), 2022.
   Paper

5. Kin Gwn Lore, Nicholas Sweet, Kundan Kumar, N Ahmed, S Sarkar
   Deep Value of Information Estimators for Collaborative Human-Machine Information Gathering
   International Conference on Cyber-Physical Systems (ICCPS), 2016.
   Paper