K. Lakshmanan

Multiscale Q-learning with linear function approximation

Shalabh Bhatnagar, K. Lakshmanan, S. Bhatnagar, 2016, Discret. Event Dyn. Syst..

Accelerated Reinforcement Learning

K. Lakshmanan, K. Lakshmanan, 2017, 2017 14th IEEE India Council International Conference (INDICON).

Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning

Ronald Ortner, Daniil Ryabko, K. Lakshmanan, 2015, ICML.

Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization

Shalabh Bhatnagar, K. Lakshmanan, S. Bhatnagar, 2016, Computational Optimization and Applications.

Smoothed Functional and Quasi-Newton Algorithms for Routing in Multi-stage Queueing Network with Constraints

Shalabh Bhatnagar, K. Lakshmanan, S. Bhatnagar, 2011, ICDCIT.

An Online Actor–Critic Algorithm with Function Approximation for Constrained Markov Decision Processes

Shalabh Bhatnagar, K. Lakshmanan, S. Bhatnagar, 2012, J. Optim. Theory Appl..

A novel Q-learning algorithm with function approximation for constrained Markov decision processes

Shalabh Bhatnagar, K. Lakshmanan, S. Bhatnagar, 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Transition Based Discount Factor for Model Free Algorithms in Reinforcement Learning

K. Lakshmanan, Ruchir Gupta, Abhinav Sharma, 2021, Symmetry.

An $$M/E_{K}/1/N$$M/EK/1/N Queueing-Inventory System with Two Service Rates Based on Queue Lengths

K. Jeganathan, S. Padmasekaran, M. Abdul Reiyas, 2017 .