Chandrashekar Lakshminarayanan


Phd Student
Stochastic Systems Lab,
Department of Computer Science and Automation
Indian Institute of Science


Areas of Interests

  • Markov Decision Processes (MDP).

  • Approximate Dynamic Programming (ADP).

  • Reinforcement Learning.

  • Stochastic Optimization.

  • Stochastic Approximation.

Research Focus in PhD

I use ideas from tropical linear algebra to develop new ADP methods and analysis for MDPs with large number states.


  • Chandrashekar Lakshminarayanan and Shalabh Bhatnagar, Approximate dynamic programming with (min, +) linear function approximation for Markov Decision Processes, In Proceedings of the 53rd IEEE Conference on Decision and Control (CDC), 2014 (link).

  • Chandrashekar Lakshminarayanan and Shalabh Bhatnagar, A Generalized Reduced Linear Program for Markov Decision Processes, to be presented at the Twenty-Ninth AAAI Conference, 2015 ( link ).

  • Chandrashekar Lakshminarayanan, Ayush Dubey, Shalabh Bhatnagar and Chithralekha Balamurugan,A Markov decision process framework for predictable job completion times on crowdsourcing platforms, Proceedings of HCOMP, pp.34-35, Pittsburgh, Nov. 2-4, 2014 ( link).