7 papers
Gradient-based Stochastic Optimization of Utility-based Shortfall Risk
Sumedh Gupte, Prashanth L. A., Sanjay P. Bhat
We consider the problems of estimation and optimization of utility-based shortfall risk (UBSR). We extend UBSR to cover possibly unbounded random variables. We cover prominent risk…
Markov Chain Variance Estimation: A Stochastic Approximation Approach
Shubhada Agrawal, Prashanth L. A., Siva Theja Maguluri
We consider the problem of estimating the asymptotic variance of a function defined on a Markov chain, an important step for statistical inference of the stationary mean. We design…
Policy Gradient Methods for Distortion Risk Measures
Nithia Vijayan, Prashanth L. A
We propose policy gradient algorithms which learn risk-sensitive policies in a reinforcement learning (RL) framework. Our proposed algorithms maximize the distortion risk measure (…
Risk-Sensitive Reinforcement Learning via Policy Gradient Search
Prashanth L. A., Michael Fu
The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumula…
Bandit algorithms to emulate human decision making using probabilistic distortions
Ravi Kumar Kolla, Prashanth L. A., Aditya Gopalan +3
Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed…
Policy Gradients for CVaR-Constrained MDPs
Prashanth L. A.
We study a risk-constrained version of the stochastic shortest path (SSP) problem, where the risk measure considered is Conditional Value-at-Risk (CVaR). We propose two algorithms…
Fast gradient descent for drifting least squares regression, with application to bandits
Nathaniel Korda, Prashanth L. A., Rémi Munos
Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using…