Search Results for author: Shaan ul Haque

Found 4 papers, 0 papers with code

Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem

no code implementations29 Oct 2024 Shaan ul Haque, Siva Theja Maguluri

Recent works studied this problem in the actor-critic framework and established finite sample bounds assuming access to a critic with certain error guarantees.

Q-Learning Stochastic Optimization

Concentration bounds for SSP Q-learning for average cost MDPs

no code implementations7 Jun 2022 Shaan ul Haque, Vivek Borkar

We derive a concentration bound for a Q-learning algorithm for average cost Markov decision processes based on an equivalent shortest path problem, and compare it numerically with the alternative scheme based on relative value iteration.

Q-Learning

Joint Probability Estimation Using Tensor Decomposition and Dictionaries

no code implementations3 Mar 2022 Shaan ul Haque, Ajit Rajwade, Karthik S. Gurumoorthy

We create a dictionary of various families of distributions by inspecting the data, and use it to approximate each decomposed factor of the product in the mixture.

Tensor Decomposition

Cannot find the paper you are looking for? You can Submit a new open access paper.