3 papers
cs.LG2026
Generalized Random Direction Newton Algorithms for Stochastic Optimization
Soumen Pachal, Prashanth L. A., Shalabh Bhatnagar +1
We present a family of generalized Hessian estimators of the objective using random direction stochastic approximation (RDSA) by utilizing only noisy function measurements. The for…
cs.LG2026
Risk-sensitive reinforcement learning using expectiles, shortfall risk and optimized certainty equivalent risk
Sumedh Gupte, Shrey Rakeshkumar Patel, Soumen Pachal +2
We propose risk-sensitive reinforcement learning algorithms catering to three families of risk measures, namely expectiles, utility-based shortfall risk and optimized certainty equ…
cs.LG2025
Policy Newton methods for Distortion Riskmetrics
Soumen Pachal, Mizhaan Prajit Maniyar, Prashanth L. A
We consider the problem of risk-sensitive control in a reinforcement learning (RL) framework. In particular, we aim to find a risk-optimal policy by maximizing the distortion riskm…