Prashanth L.A.
Associate Professor
SSB 314,
Computer Science and Engineering,
Indian Institute of Technology Madras
Chennai 600036
Email: prashla AT cse.iitm.ac.in
Tel: +91-44-22574377
Research Interests
Reinforcement Learning, Simulation Optimization, Multi-armed Bandits
News
Feb-2023: Invited talk on ‘Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation’ at Networks Seminar Series held (in-person) at Indian Institute of Science. Click here for the video.
Feb-2023: Tutorial on risk-sensitive reinforcement learning at AAAI-2023. Click here for details.
Jan-2023: A paper entitled Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation accepted for publication in AISTATS.
Jan-2023: Teaching a course on stochastic optimization. For details, click here.
Jan-2023: Invited talk on ‘A Wasserstein distance approach for concentration of empirical risk estimates’ at Information Theory and Data Science Workshop held (in-person) at National University of Singapore.
Aug-2022: A paper entitled A Wasserstein distance approach for concentration of empirical risk estimates accepted for publication in Journal of Machine Learning Research.
Jul-2022: Teaching a course on programming and data structures. For details, click here.
Jul-2022: Tutorial on Risk-Aware Multi-armed Bandits at SPCOM 2022. Slides here.
Jun-2022: A monograph entitled Risk-Sensitive Reinforcement Learning via Policy Gradient Search published by Foundations and Trends in Machine Learning.
Apr-2022: A survey article entitled A Survey of Risk-Aware Multi-Armed Bandits accepted at IJCAI-2022.
Feb-2022: Invited talk on ‘Concentration of risk measures: A Wasserstein distance approach’ at ‘IITB Workshop on Stochastic Models’.
Jan-2022: Teaching a course on object oriented analysis using C++. For details, click here.
Oct-2021: Invited talk on ‘Concentration bounds for temporal difference learning with linear function approximation: The case of batch data and uniform sampling’ at IISc workshop on Deep Reinforcement Learning. For the video recording, click here.
Aug-2021: Teaching a course on RL. For details, click here.
Aug-2021: A paper entitled Non-asymptotic bounds for stochastic optimization with biased noisy gradient oracles accepted with minor revisions for publication in IEEE Transactions on Automatic Control.
Aug-2021: Serving on the 'Senior Program Committee’ of AAAI-22.
Jul-2021: Nirav Bhavsar wins ‘Biswajit Sain MS Thesis Award 2021’.
Jul-2021: A paper entitled Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint accepted for publication in Systems and Control Letters.
Feb-2021: Teaching a course on RL. Programming assignments facilitated by Aicrowd - see here, here, and here. For course details, click here.
Dec-2020: A paper entitled Estimation of Spectral Risk Measures accepted at AAAI-21.
Sep-2020: A paper entitled Concentration bounds for temporal difference learning with linear function approximation: The case of batch data and uniform sampling accepted for publication in the Machine Learning journal.
Aug-2020: Serving on the 'Senior Program Committee’ of AAAI-21.
Aug-2020: Teaching a course on stochastic modeling and the theory of queues. For details, click here.
Jun-2020: A paper entitled Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions accepted at ICML 2020.
Jan-2020: Tutorial on reinforcement learning at CCBR-IITM. Check here
Dec-2019: Visited UMD College Park to collaborate with Prof. Michael Fu and Prof. Steve Marcus. Attended NeurIPS 2019 and ICC 2019. Visited TCS Research, Hyderabad.
Aug-2019: A paper entitled Concentration of risk measures: A Wasserstein distance approach accepted at NeurIPS 2019.
Jul-2019: A paper entitled Random directions stochastic approximation with deterministic perturbations accepted to IEEE Transactions on Automatic Control.
Jun-2019: Tutorial on reinforcement learning at the ACM India Summer School on theoretical and algorithmic aspects on Machine Learning. Hand-written notes here.
Apr-2019: A paper on Correlated bandits accepted at ICML 2019.
Jan-2019 Teaching courses on ML and bandits. For details, click here and here.
Nov-2018: Posted a survey article on “Risk-sensitive reinforcement learning: A constrained optimization viewpoint” to arxiv. Check it out here.
Nov-2018: A paper on concentration bounds for Conditional Value-at-Risk (CVaR) accepted to Operations research letters.
Aug-2018 Teaching a course on RL. For details, click here.
May-2018: DST-ECRA (Early Career Research Award).
Jan-2018: Tutorial on Simultaneous perturbation methods for simulation optimization at Indian Control Conference 2018. Slides here.
Dec-2017: A paper on Stochastic optimization using Cumulative Prospect Theory accepted to IEEE Transactions on Automatic Control.
Jul-2017: Gave a tutorial on Simultaneous perturbation methods for stochastic non-convex optimization at ACM MobiHoc 2017. Slides here.