Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton

By Ole-Christoffer Granmo. 2010

157 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling (2018, background): “Thompson Sampling has been shown to be extremely effective for bandit problems both in practice (Chapelle & Li, 2011; Granmo, 2010) and theory (Agrawal & Goyal, 2012).”
Thompson Sampling for Contextual Bandits with Linear Payoffs (2012, background): “The assumptions on the actual reward distribution are only those mentioned in Section 2.1, i.e., the R -sub-Gaussian assumption.”
Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis (2012, background): “Before Agrawal and Goyal’s recent paper [1] Thompson Sampling had been investigated in [7] as the Bayesian Learning Automaton, and in [12] where an optimistic version was also proposed; however these papers only provided weak theoretical guarantees.”
Near-Optimal Regret Bounds for Thompson Sampling (2017, background): “This is the first lower bound on the performance of a natural version of Thompson Sampling that is away from the general lower bound of Ω( √ NT ) for the multiarmed bandit problem.”
Personalized Recommendation via Parameter-Free Contextual Bandits (2015, background): “Representative work along this stream involves [8, 14, 22], which follow the Bayesian paradigm to estimate the uncertainties.”
Bandit Algorithms (2020, background): “Hazan and Kale [2011] gave an algorithm for which Rn = O(k2 √ Qt), which can be better than the worst-case bound of Exp3 or Exp3-IX when the quadratic variation is very small.”