Gambler Bandits and the Regret of Being Ruined - Intelligence Collective et Interaction Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Gambler Bandits and the Regret of Being Ruined

Résumé

In this paper we consider a particular class of problems called multiarmed gambler bandits (MAGB) which constitutes a modified version of the Bernoulli MAB problem where two new elements must be taken into account: the budget and the risk of ruin. The agent has an initial budget that evolves in time following the received rewards, which can be either +1 after a success or −1 after a failure. The problem can also be seen as a MAB version of the classic gambler's ruin game. The contribution of this paper is a preliminary analysis on the probability of being ruined given the current budget and observations, and the proposition of an alternative regret formulation, combining the classic regret notion with the expected loss due to the probability of being ruined. Finally, standard state-of-the-art methods are experimentally compared using the proposed metric.
Fichier principal
Vignette du fichier
2021___AAMAS___Survival_Bandit_Gambler__SHORT_ (6).pdf (1.85 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03120813 , version 1 (17-03-2021)

Identifiants

  • HAL Id : hal-03120813 , version 1

Citer

Filipo Studzinski Perotto, Sattar Vakili, Pratik Gajane, Yaser Faghan, Mathieu Bourgais. Gambler Bandits and the Regret of Being Ruined. 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), May 2021, London (fully virtual event), United Kingdom. ⟨hal-03120813⟩
263 Consultations
309 Téléchargements

Partager

Gmail Facebook X LinkedIn More