Profile picture for user cnarayanan
Dr. Chandra Shekar Lakshminarayanan
Asst. Professor
Email Me


My research areas are reinforcement learning, stochastic control and deep learning.  I obtained my PhD from the Department of Computer Science and Automation, Indian Institute of Science (2016), and was a post-doctoral research fellow at the Department of Computing Science (July 2016- June 2017), University of Alberta, and a research scientist at DeepMind, London (August 2017-July 2018). Prior to my PhD, I was an analog design engineer at Cosmic Circuits, Bangalore for a period of 3 years. I joined IITPKD as an assistant professor on July 2018.


Reinforcement Learning; Stochastic Control; Deep Learning


Artificial Intelligence (course/lab)

Additional Information

Chandrashekar, L and Szepesvári C., "Linear Stochastic Approximation: How far does constant step size and iterate averaging go?", AISTATS, 2018

Chandrashekar, L.; Bhatnagar, S and Szepesvári C., "A Linearly Relaxed Approximate Linear Program for Markov Decision Processes”, IEEE Transactions on Automatic Control, 2018

Chandrashekar, L. and Bhatnagar, S. “A Stability Criterion for Two Timescale Stochastic Approximation Schemes”,  Automatica, 2017

Kumar, S.; Padakandla, S.; Chandrashekar, L.; Parihar, P.; Gopinath, K.; Bhanagar, S.; "Scalable Performance Tuning of Hadoop MapReduce: A Noisy Gradient Approach", IEEE 10th International Conference on Cloud Computing, 2017

 Maity, R. K.; Chandrashekar, L.; Padakandla, S.; Bhatnagar, S., “ Shaping Proto-Value Functions Using Rewards”, European Conference on Artificial Intelligence, 2016

Chandrashekar, L.; Bhatnagar, S., “A Generalized Reduced Linear Program for Markov Decision Processes,” Twenty-Ninth AAAI conference, 2015

Chandrashekar, L.; Bhatnagar, S., “Approximate Dynamic Programming with (min, +) linear function approximation for Markov Decision Processes,” 53rd IEEE Annual Conference on Decision and Control (CDC), 2014

Chandrashekar, L.; Dubey, A.; Bhatnagar, S. and Chithralekha, B., “A Markov Decision Process framework for predictable job completion times on crowdsourc-
ing platforms”, Proceedings of the Second AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2014