activity
20192026
most citedWhen to stop value iteration: stability and near-optimality versus computation

2 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing 2024Show all

1 paper · 1 filter

math.OC2024

Policy iteration for discrete-time systems with discounted costs: stability and near-optimality guarantees

Jonathan de Brusse, Mathieu Granzotto, Romain Postoyan +1

Given a discounted cost, we study deterministic discrete-time systems whose inputs are generated by policy iteration (PI). We provide novel near-optimality and stability properties…