23 citations · 45 across the 13 of their papers we have counts for
5 papers · 1 filter
Inexact GMRES Policy Iteration for Large-Scale Markov Decision Processes
Matilde Gargiani, Dominic Liao-McPherson, Andrea Zanelli +1
Policy iteration enjoys a local quadratic rate of contraction, but its iterations are computationally expensive for Markov decision processes (MDPs) with a large number of states.…
Policy Iteration for Multiplicative Noise Output Feedback Control
Benjamin Gravell, Matilde Gargiani, John Lygeros +1
We propose a policy iteration algorithm for solving the multiplicative noise linear quadratic output feedback design problem. The algorithm solves a set of coupled Riccati equation…
Data-Driven Optimal Control of Affine Systems: A Linear Programming Perspective
Andrea Martinelli, Matilde Gargiani, Marina Draskovic +1
In this letter, we discuss the problem of optimal control for affine systems in the context of data-driven linear programming. First, we introduce a unified framework for the fixed…
Dynamic Programming Through the Lens of Semismooth Newton-Type Methods (Extended Version)
Matilde Gargiani, Andrea Zanelli, Dominic Liao-McPherson +2
Policy iteration and value iteration are at the core of many (approximate) dynamic programming methods. For Markov Decision Processes with finite state and action spaces, we show t…
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Matilde Gargiani, Andrea Zanelli, Andrea Martinelli +2
Despite their success, policy gradient methods suffer from high variance of the gradient estimate, which can result in unsatisfactory sample complexity. Recently, numerous variance…