K. Lakshmanan

I work as Assistant Professor in Indian Institute of Technology (BHU), Varanasi. Earlier I was post-doc at NUS, Montanuniversität Leoben Austria, IIT Bombay and IISc Bangalore. I completed my PhD at the Indian Institute of Science, Bangalore under Prof. Shalabh Bhatnagar in 2013 and B.Tech at Anna University,  Guindy Chennai in 2006.



1.  K. Lakshmanan and S. Bhatnagar, Quasi-Newton Smoothed Functional Algorithms for Unconstrained and Constrained Simulation Optimization, Computational Optimization and Applications, Vol 66 Issue 3, pp. 533-556, 2017 [Link] 

2.  S. Bhatnagar and Lakshmanan K., Multiscale Q-learning with Linear Function Approximation, Discrete Event Dynamic Systems,  Vol 26, Issue 3, pp. 477-509, 2016 [Link] 

3.  S. Bhatnagar and Lakshmanan K., An Online Actor–Critic Algorithm with Function Approximation for Constrained Markov Decision Processes,  Journal of Optimization Theory and Applications, Vol 153, No. 3, pp. 688-708, 2012 [Link] 


1. K. Lakshmanan, R. Ortner and D. Ryabko, Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning, JMLR Workshop and Conference Proceedings Volume 37 : Proceedings of The 32nd International Conference on Machine Learning (ICML) pp. 524-532, 2015 [Link] 

2. K.Lakshmanan and S. Bhatnagar, An Online Convergent Constrained Q-learning Algorithm with Linear Function Approximation, Invited paper at 50th Annual Allerton Conference on Communication, Control, and Computing,  pp. 400-405, 2012 [Link]

3. K. Lakshmanan and S. Bhatnagar, Smoothed Functional and Quasi-Newton Algorithms for Routing in Multi-stage Queueing Networks with Constraints, Proceedings of Distributed Computing and Internet Technology (ICDCIT), LNCS Vol. 6536, pp. 175-186, 2011 [Link]

4. R. Thilagaraj, L. Kailasam and K. Lakshmanan, Strengthening RSA Algorithm, Proceedings of the International Conference on Information Security, Pondicherry, 2005

Other Interests: