Tabular and Deep Learning of Whittle Index - Archive ouverte HAL Access content directly
Conference Poster Year :

Tabular and Deep Learning of Whittle Index


- Whittle index policy is an asymptotically optimal heuristic for solving Restless Multi-Armed Bandit Problems (RMBAP). - We propose two algorithms, QWI and QWINN, for the computation of such indices. - Both employ a two timescale system for the computation of the indices and the Q-values of each state/action.
Fichier principal
Vignette du fichier
poster.pdf (2.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03810695 , version 1 (11-10-2022)


  • HAL Id : hal-03810695 , version 1


Francisco Robledo, Urtzi Ayesta, Konstantin Avrachenkov, Vivek S Borkar. Tabular and Deep Learning of Whittle Index. EWRL 2022 - 15th European Workshop on Reinforcement Learning, Sep 2022, Milan, Italy. ⟨hal-03810695⟩
29 View
12 Download


Gmail Facebook Twitter LinkedIn More