no code implementations • 4 Jun 2024 • Francisco Robledo Relaño, Vivek Borkar, Urtzi Ayesta, Konstantin Avrachenkov
The Whittle index policy is a heuristic that has shown remarkably good performance (with guaranteed asymptotic optimality) when applied to the class of problems known as Restless Multi-Armed Bandit Problems (RMABPs).
no code implementations • 3 Jun 2024 • Francisco Robledo, Urtzi Ayesta, Konstantin Avrachenkov
This paper introduces the Lagrange Policy for Continuous Actions (LPCA), a reinforcement learning algorithm specifically designed for weakly coupled MDP problems with continuous action spaces.
no code implementations • 3 Mar 2020 • Elene Anton, Urtzi Ayesta, Matthieu Jonckheere, Ina Verloop
As such, our result is the first in showing that redundancy can improve the stability and hence performance of a system when copies are non-i. i. d..
Networking and Internet Architecture Probability