12 citations · 18 across the 15 of their papers we have counts for
9 papers · 1 filter
Policy iteration: for want of recursive feasibility, all is not lost
Mathieu Granzotto, Olivier Lindamulage De Silva, Romain Postoyan +2
This paper investigates recursive feasibility, recursive robust stability and near-optimality properties of policy iteration (PI). For this purpose, we consider deterministic nonli…
Exploiting homogeneity for the optimal control of discrete-time systems: application to value iteration
Mathieu Granzotto, Romain Postoyan, Lucian Buşoniu +2
To investigate solutions of (near-)optimal control problems, we extend and exploit a notion of homogeneity recently proposed in the literature for discrete-time systems. Assuming t…
Asynchronous Distributed Optimization via Dual Decomposition and Block Coordinate Subgradient Methods
Yankai Lin, Iman Shames, Dragan Nesic
We study the problem of minimizing the sum of potentially non-differentiable convex cost functions with partially overlapping dependences in an asynchronous manner, where communica…
A Sequential Learning Algorithm for Probabilistically Robust Controller Tuning
Robert Chin, Chris Manzie, Iman Shames +2
We introduce a sequential learning algorithm to address a robust controller tuning problem, which in effect, finds (with high probability) a candidate solution satisfying the inter…
When to stop value iteration: stability and near-optimality versus computation
Mathieu Granzotto, Romain Postoyan, Dragan Nešić +2
Value iteration (VI) is a ubiquitous algorithm for optimal control, planning, and reinforcement learning schemes. Under the right assumptions, VI is a vital tool to generate inputs…
Optimistic planning for the near-optimal control of nonlinear switched discrete-time systems with stability guarantees
Mathieu Granzotto, Romain Postoyan, Lucian Buşoniu +2
Originating in the artificial intelligence literature, optimistic planning (OP) is an algorithm that generates near-optimal control inputs for generic nonlinear discrete-time syste…