Prashanth L. A.

Publication Activity (10 Years)

Years Active: 2008-2024
Publications (10 Years): 49

Top Topics

Network Routing

Stochastic Approximation

Top Venues

IEEE Trans. Autom. Control.

Publications

Ayon Ghosh, Prashanth L. A., Krishna P. Jagannathan
Concentration Bounds for Optimized Certainty Equivalent Risk Estimation. CoRR (2024)
Akash Mondal, Prashanth L. A., Shalabh Bhatnagar
Truncated Cauchy random perturbations for smoothed functional-based stochastic optimization. Autom. 162 (2024)
Tejaram Sangadi, Prashanth L. A., Krishna P. Jagannathan
Finite Time Analysis of Temporal Difference Learning for Mean-Variance in a Discounted MDP. CoRR (2024)
Mizhaan Prajit Maniyar, Prashanth L. A., Akash Mondal, Shalabh Bhatnagar
A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning. AISTATS (2024)
Sumedh Gupte, Prashanth L. A., Sanjay P. Bhat
Optimization of utility-based shortfall risk: A non-asymptotic viewpoint. CoRR (2023)
Nithia Vijayan, Prashanth L. A.
A policy gradient approach for optimization of smooth risk measures. UAI (2023)
Shalabh Bhatnagar, Prashanth L. A.
Generalized Simultaneous Perturbation Stochastic Approximation with Reduced Estimator Bias. CISS (2023)
Gandharv Patil, Prashanth L. A., Dheeraj Nagaraj, Doina Precup
Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation. AISTATS (2023)
Mizhaan Prajit Maniyar, Akash Mondal, Prashanth L. A., Shalabh Bhatnagar
A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning. CoRR (2023)
Nirav Bhavsar, Prashanth L. A.
Nonasymptotic Bounds for Stochastic Optimization With Biased Noisy Gradient Oracles. IEEE Trans. Autom. Control. 68 (3) (2023)
Sanjay Bhat, Prashanth L. A., Gugan Thoppe
VaR\ and CVaR Estimation in a Markov Cost Process: Lower and Upper Bounds. CoRR (2023)
Prashanth L. A., Michael C. Fu
Risk-Sensitive Reinforcement Learning via Policy Gradient Search. Found. Trends Mach. Learn. 15 (5) (2022)
Dipayan Sen, Prashanth L. A., Aditya Gopalan
Adaptive Estimation of Random Vectors with Bandit Feedback. CoRR (2022)
Nithia Vijayan, Prashanth L. A.
Approximate gradient ascent methods for distortion risk measures. CoRR (2022)
Gandharv Patil, Prashanth L. A., Dheeraj Nagaraj, Doina Precup
Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation. CoRR (2022)
Akash Mondal, Prashanth L. A., Shalabh Bhatnagar
A Gradient Smoothed Functional Algorithm with Truncated Cauchy Random Perturbations for Stochastic Optimization. CoRR (2022)
Prashanth L. A., Sanjay P. Bhat
A Wasserstein Distance Approach for Concentration of Empirical Risk Estimates. J. Mach. Learn. Res. 23 (2022)
Shalabh Bhatnagar, Prashanth L. A.
Generalized Simultaneous Perturbation Stochastic Approximation with Reduced Estimator Bias. CoRR (2022)
Vincent Y. F. Tan, Prashanth L. A., Krishna P. Jagannathan
A Survey of Risk-Aware Multi-Armed Bandits. CoRR (2022)
Vincent Y. F. Tan, Prashanth L. A., Krishna P. Jagannathan
A Survey of Risk-Aware Multi-Armed Bandits. IJCAI (2022)
Arvind S. Menon, Prashanth L. A., Krishna P. Jagannathan
Online Estimation and Optimization of Utility-Based Shortfall Risk. CoRR (2021)
Nithia Vijayan, Prashanth L. A.
Likelihood ratio-based policy gradient methods for distorted risk measures: A non-asymptotic analysis. CoRR (2021)
Ajay Kumar Pandey, Prashanth L. A., Sanjay P. Bhat
Estimation of Spectral Risk Measures. AAAI (2021)
Nithia Vijayan, Prashanth L. A.
Smoothed functional-based gradient algorithms for off-policy reinforcement learning. CoRR (2021)
Nithia Vijayan, Prashanth L. A.
Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint. Syst. Control. Lett. 155 (2021)
Prashanth L. A., Nathaniel Korda, Rémi Munos
Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling. Mach. Learn. 110 (3) (2021)
Nirav Bhavsar, Prashanth L. A.
Non-Asymptotic Bounds for Zeroth-Order Stochastic Optimization. CoRR (2020)
Prashanth L. A., Shalabh Bhatnagar, Nirav Bhavsar, Michael C. Fu, Steven I. Marcus
Random Directions Stochastic Approximation With Deterministic Perturbations. IEEE Trans. Autom. Control. 65 (6) (2020)
Prashanth L. A., Krishna P. Jagannathan, Ravi Kumar Kolla
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions. ICML (2020)
Vinay Praneeth Boda, Prashanth L. A.
Correlated bandits or: How to minimize mean-squared error online. CoRR (2019)
Vinay Praneeth Boda, Prashanth L. A.
Correlated bandits or: How to minimize mean-squared error online. ICML (2019)
Sanjay P. Bhat, Prashanth L. A.
Improved Concentration Bounds for Conditional Value-at-Risk and Cumulative Prospect Theory using Wasserstein distance. CoRR (2019)
Ravi Kumar Kolla, Prashanth L. A., Sanjay P. Bhat, Krishna P. Jagannathan
Concentration bounds for empirical conditional value-at-risk: The unbounded case. Oper. Res. Lett. 47 (1) (2019)
Sanjay P. Bhat, Prashanth L. A.
Concentration of risk measures: A Wasserstein distance approach. NeurIPS (2019)
Ravi Kumar Kolla, Prashanth L. A., Krishna P. Jagannathan
Risk-aware Multi-armed Bandits Using Conditional Value-at-Risk. CoRR (2019)
Ajay Kumar Pandey, Prashanth L. A., Sanjay P. Bhat
Estimation of Spectral Risk Measures. CoRR (2019)
Ravi Kumar Kolla, Prashanth L. A., Sanjay P. Bhat, Krishna P. Jagannathan
Concentration bounds for empirical conditional value-at-risk: The unbounded case. CoRR (2018)
Cheng Jie, Prashanth L. A., Michael C. Fu, Steven I. Marcus, Csaba Szepesvári
Stochastic Optimization in a Cumulative Prospect Theory Framework. IEEE Trans. Autom. Control. 63 (9) (2018)
Prashanth L. A., Shalabh Bhatnagar, Nirav Bhavsar, Michael C. Fu, Steven I. Marcus
Random directions stochastic approximation with deterministic perturbations. CoRR (2018)
Prashanth L. A., Michael C. Fu
Risk-Sensitive Reinforcement Learning: A Constrained Optimization Viewpoint. CoRR (2018)
Aditya Gopalan, Prashanth L. A., Michael C. Fu, Steven I. Marcus
Weighted Bandits or: How Bandits Learn Distorted Values That Are Not Expected. AAAI (2017)
Prashanth L. A., Shalabh Bhatnagar, Michael C. Fu, Steven I. Marcus
Adaptive System Optimization Using Random Directions Stochastic Approximation. IEEE Trans. Autom. Control. 62 (5) (2017)
Prashanth L. A., Cheng Jie, Michael C. Fu, Steven I. Marcus, Csaba Szepesvári
Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control. ICML (2016)
Prashanth L. A., Mohammad Ghavamzadeh
Variance-constrained actor-critic algorithms for discounted and average reward MDPs. Mach. Learn. 105 (3) (2016)
Xiaowei Hu, Prashanth L. A., András György, Csaba Szepesvári
(Bandit) Convex Optimization with Biased Noisy Gradient Oracles. AISTATS (2016)
Prashanth L. A., H. L. Prasad, Shalabh Bhatnagar, Prakash Chandra
A constrained optimization perspective on actor-critic algorithms and application to network routing. Syst. Control. Lett. 92 (2016)
Aditya Gopalan, Prashanth L. A., Michael C. Fu, Steven I. Marcus
Weighted bandits or: How bandits learn distorted values that are not expected. CoRR (2016)
Xiaowei Hu, Prashanth L. A., András György, Csaba Szepesvári
(Bandit) Convex Optimization with Biased Noisy Gradient Oracles. CoRR (2016)
Sai Koti Reddy Danda, Prashanth L. A., Shalabh Bhatnagar
Improved Hessian estimation for adaptive random directions stochastic approximation. CDC (2016)
Nathaniel Korda, Prashanth L. A.
On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence. ICML (2015)
Prashanth L. A., Cheng Jie, Michael C. Fu, Steven I. Marcus
Cumulative Prospect Theory Meets Reinforcement Learning: Estimation and Control. CoRR (2015)
Prashanth L. A., H. L. Prasad, Shalabh Bhatnagar, Prakash Chandra
A constrained optimization perspective on actor critic algorithms and application to network routing. CoRR (2015)
Nathaniel Korda, Prashanth L. A., Rémi Munos
Fast Gradient Descent for Drifting Least Squares Regression, with Application to Bandits. AAAI (2015)
Prashanth L. A., Shalabh Bhatnagar
Adaptive system optimization using (simultaneous) random directions stochastic approximation. CoRR (2015)
Shalabh Bhatnagar, Prashanth L. A.
Simultaneous Perturbation Newton Algorithms for Simulation Optimization. J. Optim. Theory Appl. 164 (2) (2015)
Prashanth L. A., H. L. Prasad, Nirmit Desai, Shalabh Bhatnagar, Gargi Dasgupta
Simultaneous perturbation methods for adaptive labor staffing in service systems. Simul. 91 (5) (2015)
H. L. Prasad, Prashanth L. A., Shalabh Bhatnagar
Two-Timescale Algorithms for Learning Nash Equilibria in General-Sum Stochastic Games. AAMAS (2015)
Raphael Fonteneau, Prashanth L. A.
Simultaneous perturbation algorithms for batch off-policy search. CDC (2014)
Prashanth L. A., Nathaniel Korda, Rémi Munos
Fast LSTD Using Stochastic Approximation: Finite Time Analysis and Application to Traffic Control. ECML/PKDD (2) (2014)
Prashanth L. A.
Policy Gradients for CVaR-Constrained MDPs. ALT (2014)
H. L. Prasad, Prashanth L. A., Shalabh Bhatnagar
Algorithms for Nash Equilibria in General-Sum Stochastic Games. CoRR (2014)
Prashanth L. A.
Policy Gradients for CVaR-Constrained MDPs. CoRR (2014)
Nathaniel Korda, Prashanth L. A.
On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence. CoRR (2014)
Prashanth L. A., Abhranil Chatterjee, Shalabh Bhatnagar
Two timescale convergent Q-learning for sleep-scheduling in wireless sensor networks. Wirel. Networks 20 (8) (2014)
Prashanth L. A., Mohammad Ghavamzadeh
Actor-Critic Algorithms for Risk-Sensitive Reinforcement Learning. CoRR (2014)
Raphael Fonteneau, Prashanth L. A.
Simultaneous Perturbation Algorithms for Batch Off-Policy Search. CoRR (2014)
Prashanth L. A., Abhranil Chatterjee, Shalabh Bhatnagar
Adaptive sleep-wake control using reinforcement learning in sensor networks. COMSNETS (2014)
Nathaniel Korda, Prashanth L. A., Rémi Munos
Online gradient descent for least squares regression: Non-asymptotic bounds and application to bandits. CoRR (2013)
Prashanth L. A., H. L. Prasad, Nirmit Desai, Shalabh Bhatnagar, Gargi Dasgupta
Simultaneous Perturbation Methods for Adaptive Labor Staffing in Service Systems. CoRR (2013)
Prashanth L. A., Mohammad Ghavamzadeh
Actor-Critic Algorithms for Risk-Sensitive MDPs. NIPS (2013)
Prashanth L. A., Nathaniel Korda, Rémi Munos
Analysis of stochastic approximation for efficient least squares regression and LSTD. CoRR (2013)
Prashanth L. A., Shalabh Bhatnagar
Threshold Tuning Using Stochastic Optimization for Graded Signal Control. IEEE Trans. Veh. Technol. 61 (9) (2012)
Prashanth L. A., Shalabh Bhatnagar
Reinforcement learning with average cost for adaptive control of traffic lights at intersections. ITSC (2011)
Prashanth L. A., Shalabh Bhatnagar
Reinforcement Learning With Function Approximation for Traffic Signal Control. IEEE Trans. Intell. Transp. Syst. 12 (2) (2011)
Prashanth L. A., H. L. Prasad, Nirmit Desai, Shalabh Bhatnagar, Gargi Banerjee Dasgupta
Stochastic Optimization for Adaptive Labor Staffing in Service Systems. ICSOC (2011)
Prashanth L. A., Sajal Kumar Das, K. Gopinath
MAC Design for Heterogeneous Application Support in OFDM Based Wireless Systems. CCNC (2008)
Prashanth L. A., K. Gopinath
OFDM-MAC algorithms and their impact on TCP performance in next generation mobile networks. COMSWARE (2008)