We study online learning for optimal allocation when the resource to be allocated is time. An agent receives task proposals sequentially according to a Poisson process and can either accept or reject a proposed task. If she accepts the proposal, she is busy for the duration of the task and obtains a reward that depends on the task duration. If she rejects it, she remains on hold until a new task proposal arrives. We study the regret incurred by the agent, first when she knows her reward function but does not know the distribution of the task duration, and then when she does not know her reward function, either. This natural setting bears similarities with contextual (one-armed) bandits, but with the crucial difference that the normalized reward associated to a context depends on the whole distribution of contexts.

Making the most of your day: online learning for optimal allocation of time / Boursier, E.; Garrec, T.; Perchet, V.; Scarsini, M.. - Advances in Neural Information Processing Systems, (2021), pp. 11208-11219. (NeurIPS 2021, Virtual, Online, 6 December 2021 through 14 December 2021).

Making the most of your day: online learning for optimal allocation of time

Scarsini M.
2021

Abstract

We study online learning for optimal allocation when the resource to be allocated is time. An agent receives task proposals sequentially according to a Poisson process and can either accept or reject a proposed task. If she accepts the proposal, she is busy for the duration of the task and obtains a reward that depends on the task duration. If she rejects it, she remains on hold until a new task proposal arrives. We study the regret incurred by the agent, first when she knows her reward function but does not know the distribution of the task duration, and then when she does not know her reward function, either. This natural setting bears similarities with contextual (one-armed) bandits, but with the crucial difference that the normalized reward associated to a context depends on the whole distribution of contexts.
File in questo prodotto:
File Dimensione Formato  
NeurIPS2021BGPS.pdf

Open Access

Tipologia: Versione dell'editore
Licenza: Tutti i diritti riservati
Dimensione 715.91 kB
Formato Adobe PDF
715.91 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11385/219158
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact