- Conference Paper
Partial monitoring is a rich framework for sequential decision making under uncertainty that generalizes many well known bandit models, including linear, combinatorial and dueling bandits. We introduce information directed sampling (IDS) for stochastic partial monitoring with a linear reward and observation structure. IDS achieves adaptive worst-case regret rates that depend on precise observability conditions of the game. Moreover, we prove lower bounds that classify the minimax regret of all finite games into four possible regimes. IDS achieves the optimal rate in all cases up to logarithmic factors, without tuning any hyper-parameters. We further extend our results to the contextual and the kernelized setting, which significantly increases the range of possible applications. Show more
Book titleProceedings of Thirty Third Conference on Learning Theory
Journal / seriesProceedings of Machine Learning Research
Pages / Article No.
SubjectInformation directed sampling; Linear partial monitoring; Bandits
Organisational unit03908 - Krause, Andreas / Krause, Andreas
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
NotesDue to the Coronavirus (COVID-19) the conference was conducted virtually.
MoreShow all metadata