36 citations · 82 across the 30 of their papers we have counts for
3 papers · 1 filter
Finite Sample Analyses for TD(0) with Function Approximation
Gal Dalal, Balázs Szörényi, Gugan Thoppe +1
TD(0) is one of the most commonly used algorithms in reinforcement learning. Despite this, there is no existing finite sample analysis for TD(0) with function approximation, even f…
Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning
Gal Dalal, Balazs Szorenyi, Gugan Thoppe +1
Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In t…
Randomly Weighted complexes: Minimal Spanning Acycles and Persistence Diagrams
Primoz Skraba, Gugan Thoppe, D. Yogeshwaran
A weighted complex is a simplicial complex of dimension in which each face is assigned a real-valued weight. We derive three key results here concerning persistence diagram…