RL : Reinforcement Learning and Stochastic Optimization LabLink to Lab Webpage

Research AreasReinforcement Learning.
MembersFaculty : L A Prashanth.

Students/Scholars :

Project Staffs :

Recent Publications
  • A policy gradient approach for optimization of smooth risk measures.  
           Nithia Vijayan , L A Prashanth
          Appeared in Uncertainty in Artificial Intelligence, UAI 2023, July 31 - 4 August 2023, Pittsburgh, PA, USA., Proceedings of Machine Learning Research, Vol 216, pp.2168-2178, Aug 2023
  • Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation.  
           Gandharv Patil , L A Prashanth , Dheeraj Nagaraj , Doina Precup
          Appeared in International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain., Proceedings of Machine Learning Research, Vol 206, pp.5438-5448, Apr 2023
  • Generalized Simultaneous Perturbation Stochastic Approximation with Reduced Estimator Bias.  
           Shalabh Bhatnagar , L A Prashanth
          Appeared in 57th Annual Conference on Information Sciences and Systems, CISS 2023, Baltimore, MD, USA, March 22-24, 2023, pp.1-6, Mar 2023
  • Nonasymptotic Bounds for Stochastic Optimization With Biased Noisy Gradient Oracles.  
           Nirav Bhavsar , L A Prashanth
          Appeared in IEEE Trans. Autom. Control., Vol 68, pp.1628-1641, Jan 2023
  • A Wasserstein Distance Approach for Concentration of Empirical Risk Estimates.  
           L A Prashanth , Sanjay P. Bhat
          Appeared in J. Mach. Learn. Res., Vol 23, pp.238:1-238:61, Jan 2022

Sponsored Projects

    © 2016 - All Rights Reserved - Dept of CSE, IIT Madras
    Website Credits