Bandit processes and dynamic allocation indices
Abstract
Summary The paper aims to give a unified account of the central concepts in recent work on bandit processes and dynamic allocation indices; to show how these reduce some previously intractable problems to the problem of calculating such indices; and to describe how these calculations may be carried out. Applications to stochastic scheduling, sequential clinical trials and a class of search problems are discussed.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Finding an analytical solution to the Bayes-optimal policy in MDPs is extremely challenging and only possible for a few special cases.
“Finding an analytical solution to Equation 9 is extremely challenging and indeed only possible for a few special cases (Duff, 2003; Gittins, 1979), which made it historically near impossible to investigate such problems within the framework of rational analysis.”
From Meta-learned models of cognition (2024) · cites this paper as Gittins, 1979
Cited by
Sorted by citations
A contextual-bandit approach to personalized news article recommendation
Li, L., Chu, W., Langford, J., & Schapire, R. E. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772758 · Cited by 2,562 · see citing works
Cohen, J. D., McClure, S. M., & Yu, A. J. (2007) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2007.2098 · Cited by 1,121 · see citing works
Humans use directed and random exploration to solve the explore–exploit dilemma.
Wilson, R. C., Geana, A., White, J. M., Ludvig, E. A., & Cohen, J. D. (2014) · Journal of Experimental Psychology: General · doi:10.1037/a0038199 · Cited by 580 · see citing works
Learning to reinforcement learn
Wang, J. X., Kurth-Nelson, Z., Tirumala, D., Soyer, H., Leibo, J. Z., Munos, R., Blundell, C., Kumaran, D., & Botvinick, M. (2016) · arXiv · doi:10.48550/arxiv.1611.05763 · Cited by 579 · see citing works
Satisficing: Integrating Two Traditions
Artinger, F. M., Gigerenzer, G., & Jacobs, P. (2022) · Journal of Economic Literature · doi:10.1257/jel.20201396 · Cited by 90 · see citing works
Learning State Selection for Reconfigurable Antennas: A Multi-Armed Bandit Approach
Gulati, N., & Dandekar, K. R. (2014) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2013.2276414 · Cited by 69 · see citing works
Meta-learned models of cognition
Binz, M., Dasgupta, I., Jagadish, A. K., Botvinick, M., Wang, J. X., & Schulz, E. (2024) · Behavioral and Brain Sciences · doi:10.1017/s0140525x23003266 · Cited by 38 · see citing works
Kuo, P.-C., Hou, H., Dabney, W., & Walker, E. Y. (2025) · arXiv
“Two-armed Bernoulli bandit The Bayes-optimal solution can be derived using the Gittins index method [52].”
- Authors
- Gittins, J. C.
- Affiliations
- University of Oxford (GB)
- Corresponding author
- Gittins, J. C.
- Venue
- Journal of the Royal Statistical Society Series B: Statistical Methodology
- Publisher
- Oxford University Press (OUP)
- Published
- 1979-01-01
- Volume
- 41
- Issue
- 2
- Pages
- 148-164
- ISSN
- 1369-7412 (ISSN-L)
- 1467-9868
- OpenAlex
- W3125634603
- Cited by
- 1,487
- References
- 0
- Citations by year
- 2026: 37 · 2025: 43 · 2024: 61 · 2023: 46 · 2022: 58 · 2021: 95 · 2020: 119 · 2019: 67 · 2018: 70 · 2017: 60 · 2016: 83 · 2015: 72 · 2014: 76 · 2013: 65 · 2012: 46
- FWCI
- 14.67
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Journal of the Royal Statistical Society Series B (Statistical Methodology) (publishedVersion)
- Funders
- University of Sussex
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
- Physical Sciences › Computer Science › Computer Networks and Communications › Optimization and Search Problems
- Social Sciences › Decision Sciences › Management Science and Operations Research › Simulation Techniques and Applications
- Keywords
- sequential allocation, stochastic scheduling, sequential clinical trials, search problems, sequential decision making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
