A note on structural properties of the Bernoulli two-armed bandit problem
From MaRDI portal
Publication:4742584
DOI10.1080/02331938208842808zbMath0505.90080MaRDI QIDQ4742584
Radu Theodorescu, Dieter Kalin
Publication date: 1982
Published in: Mathematische Operationsforschung und Statistik. Series Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/02331938208842808
finite horizon; monotonicity property; Bernoulli two-armed bandit problem; optimal expected cumulative discounted reward
90C39: Dynamic programming
Related Items
On monotone optimal decision rules and the stay-on-a-winner rule for the two-armed bandit, On the Bernoulli three-armed bandit problem, A Two-Armed Bandit Problem with possibility of no Information