The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Indexability of Restless Bandit Problems and Optimality of Whittle Index for Dynamic Multichannel Access
Abstract
In this paper, we consider a class of restless multiarmed bandit processes (RMABs) that arises in dynamic multichannel access, user/server scheduling, and optimal activation in multiagent systems. For this class of RMABs, we establish the indexability and obtain Whittle index in closed form for both discounted and average reward criteria. These results lead to a direct implementation of Whittle index policy with remarkably low complexity. When arms are stochastically identical, we show that Whittle index policy is optimal under certain conditions. Furthermore, it has a semiuniversal structure that obviates the need to know the Markov transition probabilities. The optimality and the semiuniversal structure result from the equivalence between Whittle index policy and the myopic policy established in this work. For nonidentical arms, we develop efficient algorithms for computing a performance upper bound given by Lagrangian relaxation. The tightness of the upper bound and the near-optimal performance of Whittle index policy are illustrated with simulation examples.
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
THOMPSON, W. R. (1933) · Biometrika · doi:10.1093/biomet/25.3-4.285 · Cited by 2,712
A Survey of Dynamic Spectrum Access
Zhao, Q., & Sadler, B. M. (2007) · IEEE Signal Processing Magazine · doi:10.1109/msp.2007.361604 · Cited by 2,698
Self-citationCapacity of a Burst-Noise Channel
Gilbert, E. N. (1960) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1960.tb03959.x · Cited by 2,313
Decentralized cognitive MAC for opportunistic spectrum access in ad hoc networks: A POMDP framework
Zhao, Q., Tong, L., Swami, A., & Chen, Y. (2007) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2007.070409 · Cited by 1,587
Self-citationBandit processes and dynamic allocation indices
Gittins, J. C. (1979) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1979.tb01068.x · Cited by 1,487
The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
Smallwood, R. D., & Sondik, E. J. (1973) · Operations Research · doi:10.1287/opre.21.5.1071 · Cited by 1,479
Restless bandits: activity allocation in a changing world
Whittle, P. (1988) · Journal of Applied Probability · doi:10.1017/s0021900200040420 · Cited by 1,173
Gallager, R. G. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600329 · Cited by 691
Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
Arapostathis, A., Borkar, V. S., Fernández-Gaucherand, E., Ghosh, M. K., & Marcus, S. I. (1993) · SIAM Journal on Control and Optimization · doi:10.1137/0331018 · Cited by 592
Sondik, E. J. (1978) · Operations Research · doi:10.1287/opre.26.2.282 · Cited by 536
Gallager, R. G. (1996) · doi:10.1007/978-1-4615-2329-1 · Cited by 494
On an index policy for restless bandits
Weber, R., & Weiss, G. (1990) · Journal of Applied Probability · doi:10.1017/s0021900200039176 · Cited by 486
The Complexity of Optimal Queuing Network Control
Papadimitriou, C. H., & Tsitsiklis, J. N. (1999) · Mathematics of Operations Research · doi:10.1287/moor.24.2.293 · Cited by 469
Chen, Y., Zhao, Q., & Swami, A. (2008) · IEEE Transactions on Information Theory · doi:10.1109/tit.2008.920248 · Cited by 421
Self-citationMulti-armed bandits in metric spaces
Kleinberg, R., Slivkins, A., & Upfal, E. (2008) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/1374376.1374475 · Cited by 396
Optimality of Myopic Sensing in Multichannel Opportunistic Access
Ahmad, S. H. A., Liu, M., Javidi, T., Zhao, Q., & Krishnamachari, B. (2009) · IEEE Transactions on Information Theory · doi:10.1109/tit.2009.2025561 · Cited by 364
Self-citationOn myopic sensing for multi-channel opportunistic access: structure, optimality, and performance
Zhao, Q., Krishnamachari, B., & Liu, K. (2008) · IEEE Transactions on Wireless Communications · doi:10.1109/t-wc.2008.071349 · Cited by 360
Self-citationAnantharam, V., Varaiya, P., & Walrand, J. (1987) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1987.1104491 · Cited by 358
Error statistics in data transmission over fading channels
Zorzi, M., Rao, R. R., & Milstein, L. B. (1998) · IEEE Transactions on Communications · doi:10.1109/26.729391 · Cited by 261
Mahajan, A., & Teneketzis, D. (2008) · Foundations and Applications of Sensor Management · doi:10.1007/978-0-387-49819-5_6 · Cited by 185
Dynamic priority allocation via restless bandit marginal productivity indices
Niño‐Mora, J. (2007) · Top · doi:10.1007/s11750-007-0025-0 · Cited by 136
Approximation algorithms for restless bandit problems
Guha, S., Munagala, K., & Shi, P. (2010) · Journal of the ACM · doi:10.1145/1870103.1870106 · Cited by 122
Whittle's index policy for a multi-class queueing system with convex holding costs
O'Keeffe, M., Ansell, P. S., Glazebrook, K. D., & Niño‐Mora, J. (2003) · Mathematical Methods of Operations Research · doi:10.1007/s001860200257 · Cited by 108
Multi-channel opportunistic access: A case of restless bandits with multiple plays
Ahmad, S. H. A., & Liu, M. (2009) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2009.5394517 · Cited by 96
What do discounted optima converge to?: A theory of discount rate asymptotics in economic models
Dutta, P. K. (1991) · Journal of Economic Theory · doi:10.1016/0022-0531(91)90059-d · Cited by 89
Some indexable families of restless bandit problems
Glazebrook, K. D., Ruiz-Hernández, D., & Kirkbride, C. (2006) · Advances in Applied Probability · doi:10.1017/s000186780000121x · Cited by 83
Index Policies for Real-Time Multicast Scheduling for Wireless Broadcast Systems
Raghunathan, V., Borkar, V. S., Cao, M., & Kumar, P. R. (2008) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2008.217 · Cited by 73
Cited by
Age of Information: An Introduction and Survey
Yates, R. D., Sun, Y., Brown, D. R., Kaul, S. K., Modiano, E., & Ulukus, S. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3065072 · Cited by 1,160
Deep Multi-User Reinforcement Learning for Distributed Dynamic Spectrum Access
Naparstek, O., & Cohen, K. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2018.2879433 · Cited by 477
Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks
Wang, S., Liu, H., Gomes, P. H., & Krishnamachari, B. (2018) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2018.2809722 · Cited by 477
Deep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks
Liang, L., Ye, H., Yu, G., & Li, G. Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2957798 · Cited by 282
A Deep Actor-Critic Reinforcement Learning Framework for Dynamic Multichannel Access
Zhong, C., Lu, Z., Gursoy, M. C., & Velipasalar, S. (2019) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2019.2952909 · Cited by 123
Metadata
- Authors
- Liu, K., & Zhao, Q.
- Venue
- IEEE Transactions on Information Theory
- Published
- 2010-11
- Volume
- 56
- Issue
- 11
- Pages
- 5547-5567
- ISSN
- 0018-9448 (ISSN-L)
- 1557-9654
- OpenAlex
- W2141515329
- Cited by
- 347
- References
- 27
- Type
- paratext
- 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.