7 papers
Logarithmic Regret via Passive Change Detection in Piecewise-Stationary Self-Tuning Regulation
A. Ch. Madhusudanarao, Rahul Singh
We study minimum-variance control of an unknown autoregressive system with exogenous inputs and coefficients that change at unknown times. Under bounded independent disturbances, f…
Stationary Bias and Extrapolation in Nonlinear Two-Timescale Stochastic Approximation
A. Ch. Madhusudanarao, Rahul Singh
Constant-step stochastic approximation generally has a nonzero stationary mean error that persists under time averaging. This paper studies that error for nonlinear two-timescale r…
Robustness Verification of Binary Neural Networks: An Ising and Quantum-Inspired Framework
Rahul Singh, Seyran Saeedi, Zheng Zhang
Binary neural networks (BNNs) are increasingly deployed in edge computing applications due to their low hardware complexity and high energy efficiency. However, verifying the robus…
Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains
Rahul Singh, Siddharth Chandak, Eric Moulines +2
We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We fi…
Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces
Avik Kar, Rahul Singh
We study infinite-horizon average-reward reinforcement learning (RL) for Lipschitz MDPs, a broad class that subsumes several important classes such as linear and RKHS MDPs, functio…
Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning
Avik Kar, Rahul Singh
We study the infinite-horizon average-reward reinforcement learning (RL) for continuous space Lipschitz MDPs in which an agent can play policies from a given set . The proposed…
On Learning for Ambiguous Chance Constrained Problems
A Ch Madhusudanarao, Rahul Singh
We study chance constrained optimization problems s.t. where is the violation probability, when the distribut…