L A Prashanth Home Page
Associate Professor
Email : prashla [at] cse [dot] iitm [dot] ac [dot] in   |   Phone : 4377

Link to Personal Homepage

Research Interests :

Reinforcement Learning, Stochastic Optimization, Multi-armed Bandits.

Publications : (Last Five, while at IITM)DBLP | View All

  • Estimation of Spectral Risk Measures. 
    Authors : Ajay Kumar Pandey, L A Prashanth, Sanjay P. Bhat
    Appeared in Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp.12166-12173, Feb 2021
  • Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling. 
    Authors : L A Prashanth, Nathaniel Korda, Rmi Munos
    Appeared in Mach. Learn., Vol 110, pp.559-618, Jan 2021
  • Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint. 
    Authors : Nithia Vijayan, L A Prashanth
    Appeared in Syst. Control. Lett., Vol 155, pp.104988, Jan 2021
  • Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions. 
    Authors : L A Prashanth, Krishna P. Jagannathan, Ravi Kumar Kolla
    Appeared in Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. (ICML 2020) ,Proceedings of Machine Learning Research, Vol 119, pp.5577-5586, Jul 2020
  • Random Directions Stochastic Approximation With Deterministic Perturbations. 
    Authors : L A Prashanth, Shalabh Bhatnagar, Nirav Bhavsar, Michael C. Fu 0001, Steven I. Marcus
    Appeared in IEEE Trans. Autom. Control., Vol 65, pp.2450-2465, Jan 2020

(Recent) Teaching : View All  |  Back to top

Jan 2022 - Apr 2022 : - Object Oriented Algorithms Implementation and Analysis Lab (CS2810)
Jan 2022 - Apr 2022 : - Topics in Reinforcement Learning (CS7011)
Jan 2022 - Apr 2022 : - Stochastic Optimization (CS6515)
Aug 2021 - Dec 2021 : - Reinforcement learning (CS6700)
Feb 2021 - May 2021 : - Reinforcement learning (CS6700)

(Current) Advisees View All  |  Back to top

ProgramNameRoll No.Joining DateFunding
PhDNithia VCS17D003Jul 2017HTRA
MSAjay Kumar PandeyCS17S011Jul 2017HTRA
MSDipayan SenCS18S012Jul 2018HTRA