The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
Abstract
We consider a non-Bayesian infinite horizon version of the multi-armed bandit problem with the objective of designing simple policies whose regret increases slowly with time. In their seminal work on this problem, Lai and Robbins had obtained a O(log n) lower bound on the regret with a constant that depends on the Kullback–Leibler number. They also constructed policies for some specific families of probability distributions (including exponential families) that achieved the lower bound. In this paper we construct index policies that depend on the rewards from each arm only through their sample mean. These policies are computationally much simpler and are also applicable much more generally. They achieve a O(log n) regret with a constant that is also based on the Kullback–Leibler number. This constant turns out to be optimal for one-parameter exponential families; however, in general it is derived from the optimal one via a ‘contraction' principle. Our results rely entirely on a few key lemmas from the theory of large deviations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Asymptotically efficient adaptive allocation rules
Lai, T. L., & Robbins, H. (1985) · Advances in Applied Mathematics · doi:10.1016/0196-8858(85)90002-8 · Cited by 2,406
Chaghaghi, F. S., & Billingsley, P. (1986) · The Statistician · doi:10.2307/2987970 · Cited by 1,217
Entropy, Large Deviations, and Statistical Mechanics
Ellis, R. S. (1985) · Grundlehren der mathematischen Wissenschaften · doi:10.1007/978-1-4613-8533-2 · Cited by 1,196
Entropy, Large Deviations, and Statistical Mechanics
Ellis, R. S. (2006) · Classics in Mathematics · doi:10.1007/3-540-29060-5 · Cited by 1,134
Fundamentals of statistical exponential families with applications in statistical decision theory
Brown, L. D. (1986) · SPIE eBooks · doi:10.1214/lnms/1215466757 · Cited by 573
Anantharam, V., Varaiya, P., & Walrand, J. (1987) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1987.1104491 · Cited by 358
Adaptive Treatment Allocation and the Multi-Armed Bandit Problem
Lai, T. L. (1987) · The Annals of Statistics · doi:10.1214/aos/1176350495 · Cited by 279
Anantharam, V., Varaiya, P., & Walrand, J. C. (1987) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1987.1104485 · Cited by 111
Agrawal, R. K., Hedge, M. V., & Teneketzis, D. (1988) · IEEE Transactions on Automatic Control · doi:10.1109/9.7243 · Cited by 110
Self-citationCertainty equivalence control with forcing: revisited
Agrawal, R. K., & Teneketzis, D. (1989) · Systems & Control Letters · doi:10.1016/0167-6911(89)90107-2 · Cited by 15
Self-citation
Cited by
Finite-time Analysis of the Multiarmed Bandit Problem
Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002) · Machine Learning · doi:10.1023/a:1013689704352 · Cited by 6,033
Deep Reinforcement Learning with Double Q-Learning
Van Hasselt, H., Guez, A., & Silver, D. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10295 · Cited by 3,318
“The overestimations should not be confused with optimism in the face of uncertainty (Sutton, 1990; Agrawal, 1995; Kaelbling et al., 1996; Auer et al., 2002; Brafman and Tennenholtz, 2003; Szita and Lőrincz, 2008; Strehl et al., 2009), where an exploration bonus is given to states or actions with…”
BackgroundA Survey of Monte Carlo Tree Search Methods
Browne, C. B., Powley, E., Whitehouse, D., Lucas, S. M., Cowling, P. I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., & Colton, S. (2012) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2012.2186810 · Cited by 2,970
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
“In contrast to the unguided exploration strategy adopted by greedy, another class of algorithms generally known as upper confidence bound algorithms [4, 7, 17] use a smarter way to balance exploration and exploitation.”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
Bubeck, S. (2012) · now publishers, Inc. eBooks · doi:10.1561/9781601986276 · Cited by 1,404
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
Zhang, K., Yang, Z., & Başar, T. (2021) · Studies in Systems, Decision and Control · doi:10.1007/978-3-030-60990-0_12 · Cited by 1,264
Lattimore, T., & Szepesvári, C. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108571401 · Cited by 976
On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
Kaufmann, E., Cappé, O., & Garivier, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.4443 · Cited by 661
Continuously adaptive continuous queries over streams
Madden, S., Shah, M., Hellerstein, J. M., & Raman, V. (2002) · Proceedings of the 2002 ACM SIGMOD international conference on Management of data · doi:10.1145/564691.564698 · Cited by 583
(2008) · ScholarlyCommons (University of Pennsylvania) · Cited by 581
Exploration–exploitation tradeoff using variance estimates in multi-armed bandits
Audibert, J.-Y., Munos, R., & Szepesvári, C. (2009) · Theoretical Computer Science · doi:10.1016/j.tcs.2009.01.016 · Cited by 569
Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms
Li, L., Chu, W., Langford, J., & Wang, X. (2011) · Proceedings of the fourth ACM international conference on Web search and data mining · doi:10.1145/1935826.1935878 · Cited by 443
On Upper-Confidence Bound Policies for Switching Bandit Problems
Garivier, A., & Moulines, E. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24412-4_16 · Cited by 442
Linearly Parameterized Bandits
Rusmevichientong, P., & Tsitsiklis, J. N. (2010) · Mathematics of Operations Research · doi:10.1287/moor.1100.0446 · Cited by 427
Gai, Y., Krishnamachari, B., & Jain, R. (2012) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2011.2181864 · Cited by 413
A modern Bayesian look at the multi‐armed bandit
Scott, S. L. (2010) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.874 · Cited by 406
Distributed Learning in Multi-Armed Bandit With Multiple Players
Liu, K., & Zhao, Q. (2010) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2010.2062509 · Cited by 385
Derivative-free optimization methods
Larson, J., Menickelly, M., & Wild, S. M. (2019) · Acta Numerica · doi:10.1017/s0962492919000060 · Cited by 381
The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond
Garivier, A., & Cappé, O. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1102.2490 · Cited by 326
Customer Acquisition via Display Advertising Using Multi-Armed Bandit Experiments
Schwartz, E. M., Bradlow, E. T., & Fader, P. S. (2017) · Marketing Science · doi:10.1287/mksc.2016.1023 · Cited by 260
Computational mechanisms of curiosity and goal-directed exploration
Schwartenbeck, P., Passecker, J., Hauser, T. U., FitzGerald, T. H., Kronbichler, M., & Friston, K. J. (2019) · eLife · doi:10.7554/elife.41703 · Cited by 254
Dynamic Online Pricing with Incomplete Information Using Multiarmed Bandit Experiments
Misra, K., Schwartz, E. M., & Abernethy, J. (2019) · Marketing Science · doi:10.1287/mksc.2018.1129 · Cited by 183
Metadata
- Authors
- Agrawal, R.
- Venue
- Advances in Applied Probability
- Publisher
- Cambridge University Press (CUP)
- Published
- 1995-12
- Volume
- 27
- Issue
- 4
- Pages
- 1054-1078
- ISSN
- 0001-8678 (ISSN-L)
- 1475-6064
- OpenAlex
- W2000080679
- Cited by
- 540
- References
- 10
- FWCI
- 1.36
- Type
- journal article
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.