We consider n-player repeated games where one optimizer plays against no-regret players. In a 2-player game, the optimizer can always guarantee an expected average utility of at least the Stackelberg value per round. However, if there are several players, this result does not hold, and the optimizer can guarantee at least the correlated Stackelberg value per round. Finally, we can obtain the same result almost surely and not in expectation. (c) 2023 Elsevier B.V. All rights reserved.
Playing against no-regret players / D'Andrea, Maurizio. - In: OPERATIONS RESEARCH LETTERS. - ISSN 0167-6377. - 51:2(2023), pp. 142-145. [10.1016/j.orl.2023.01.005]
Playing against no-regret players
D'Andrea, M
2023
Abstract
We consider n-player repeated games where one optimizer plays against no-regret players. In a 2-player game, the optimizer can always guarantee an expected average utility of at least the Stackelberg value per round. However, if there are several players, this result does not hold, and the optimizer can guarantee at least the correlated Stackelberg value per round. Finally, we can obtain the same result almost surely and not in expectation. (c) 2023 Elsevier B.V. All rights reserved.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Playing against no regret players.pdf
Solo gestori archivio
Tipologia:
Versione dell'editore
Licenza:
Tutti i diritti riservati
Dimensione
225.66 kB
Formato
Adobe PDF
|
225.66 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
