Browse State-of-the-Art › Multi-Armed Bandits
Multi-Armed Bandits
253 papers with code · 1 benchmark · 2 datasets archive 2025-07-28
Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.
( Image credit: Microsoft Research )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Mushroom (2 rows) | Linear FullPosterior-MR | Deep Bayesian Bandits Showdown: An Empirical Comparison of... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 1,262 · with a code link: 253 · where Syntology ran a sample: 55 (44 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (55 of 1,262 tagged: 44 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument)
Page 1 of 13: papers 1 to 100 of 1,262, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
29 Oct 2018 5 repositories listedThe DRR framework treats recommendation as a sequential decision making procedure and adopts an "Actor-Critic" reinforcement learning scheme to model the interactions between the users and recommender systems, which can…
-
11 Nov 2019 4 repositories listedTo the best of our knowledge, it is the first neural network-based contextual bandit algorithm with a near-optimal regret guarantee.
-
26 Feb 2018 4 repositories listedAt the same time, advances in approximate Bayesian methods have made posterior approximation for flexible neural network models practical.
-
5 Apr 2024 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)We focus on hypothesis generation based on data (i. e., labeled examples).
-
13 Feb 2022 3 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples) · 1 pointer-only (licence)Unfortunately, when the number of actions is large, existing OPE estimators -- most of which are based on inverse propensity score weighting -- degrade severely and can suffer from extreme bias and variance.
-
7 Feb 2021 3 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 6 harvested samples)To alleviate this, we propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online.
-
10 Jun 2020 3 repositories listedWe propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks.
-
1 Jun 2020 3 repositories listedWe study locally differentially private (LDP) bandits learning in this paper.
-
31 Jul 2018 3 repositories listedWe argue that less expressive discriminators are smoother and have a general coarse grained view of the modes map, which enforces the generator to cover a wide portion of the data distribution support.
-
4 Dec 2016 3 repositories listedWe study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model.
-
18 Jul 2024 2 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 8 pointer-only (licence)Thompson Sampling is a principled method for balancing exploration and exploitation, but its real-world adoption faces computational challenges in large-scale or non-conjugate settings.
-
10 Apr 2024 2 repositories listed Syntology official (archive's flag): 6 ran · 10 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 6 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples) · 4 pointer-only (licence)We study the generalized linear contextual bandit problem within the constraints of limited adaptivity.
-
9 Nov 2023 2 repositories listedThis paper addresses both challenges by introducing the Mixture Adaptive Design (MAD), a new experimental design for multi-armed bandit (MAB) algorithms that enables anytime-valid inference on the Average Treatment…
-
26 Feb 2023 2 repositories listed Syntology official (archive's flag): 7 ran · 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 17 harvested samples)It can be shown that our estimator contains the recently proposed sharp estimator by Dorn and Guo (2022) as a special case, and our method enables a novel extension of the classical marginal sensitivity model using…
-
23 Feb 2022 2 repositories listedThis paper considers contextual bandits with a finite number of arms, where the contexts are independent and identically distributed d-dimensional random vectors, and the expected rewards are linear in both the arm…
-
3 Feb 2022 2 repositories listedWe show that the proposed estimator is unbiased in more cases compared to existing estimators that make stronger assumptions.
-
5 Nov 2021 2 repositories listedWe consider policies based on a GP and a Student's t-process (TP).
-
13 Jul 2021 2 repositories listedUnderstanding a decision-maker's priorities by observing their behavior is critical for transparency and accountability in decision processes, such as in healthcare.
-
22 Oct 2020 2 repositories listedWe consider a variant of the best arm identification task in stochastic multi-armed bandits.
-
2 Oct 2020 2 repositories listed Syntology official (archive's flag): 2 ran · 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems.
-
14 Sep 2020 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Conservation efforts in green security domains to protect wildlife and forests are constrained by the limited availability of defenders (i. e., patrollers), who must patrol vast areas to protect from attackers (e. g.…
-
18 Jun 2020 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)We consider off-policy evaluation in the contextual bandit setting for the purpose of obtaining a robust off-policy selection strategy, where the selection strategy is evaluated based on the value of the chosen policy…
-
11 Jun 2020 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 5 unverified (of 5 harvested samples) · 5 pointer-only (licence)Current state-of-the-art k-medoids clustering algorithms, such as Partitioning Around Medoids (PAM), are iterative and are quadratic in the dataset size n for each iteration, being prohibitively expensive for large…
-
24 Feb 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)This finding diverges from the notion of free exploration, which relates to covariate variation, as recently discussed in contextual bandit literature.
-
31 Dec 2019 2 repositories listedI present first-order and second-order algorithms for online learning with convex losses, in Euclidean and non-Euclidean settings.
-
6 Nov 2019 2 repositories listedWe consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated.
-
20 Jun 2019 2 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)Efficient optimisation of black-box problems that comprise both continuous and categorical inputs is important, yet poses significant challenges.
-
9 Jun 2019 2 repositories listedWe propose new estimators for OPE based on empirical likelihood that are always more efficient than IS, SNIS, and DR and satisfy the same stability and boundedness properties as SNIS.
-
11 Nov 2018 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 5 unverified (of 5 harvested samples)This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box…
-
21 Sep 2018 2 repositories listedMotivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players…
-
17 Aug 2018 2 repositories listed
-
12 Mar 2018 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
2 Oct 2015 2 repositories listed
-
15 Sep 2012 2 repositories listed
-
29 Sep 2008 2 repositories listed
-
17 Jun 2025 1 repository listed
-
3 Jun 2025 1 repository listed
-
2 Jun 2025 1 repository listed
-
24 May 2025 1 repository listed
-
21 May 2025 1 repository listed
-
2 Apr 2025 1 repository listed
-
20 Mar 2025 1 repository listed
-
19 Mar 2025 1 repository listed
-
11 Mar 2025 1 repository listed
-
27 Feb 2025 1 repository listed
-
21 Feb 2025 1 repository listed
-
12 Feb 2025 1 repository listed
-
7 Feb 2025 1 repository listed
-
31 Jan 2025 1 repository listed
-
29 Jan 2025 1 repository listed
-
18 Dec 2024 1 repository listed
-
11 Dec 2024 1 repository listed
-
15 Nov 2024 1 repository listed
-
8 Nov 2024 1 repository listed
-
8 Nov 2024 1 repository listed
-
3 Nov 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
31 Oct 2024 1 repository listed
-
17 Oct 2024 1 repository listed
-
2 Oct 2024 1 repository listed
-
2 Sep 2024 1 repository listed
-
10 Aug 2024 1 repository listed
-
8 Aug 2024 1 repository listed
-
6 Aug 2024 1 repository listed
-
27 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
18 Jun 2024 1 repository listed
-
14 Jun 2024 1 repository listed
-
6 Jun 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
28 May 2024 1 repository listed
-
28 May 2024 1 repository listed
-
9 May 2024 1 repository listed
-
26 Apr 2024 1 repository listed
-
10 Apr 2024 1 repository listed
-
24 Feb 2024 1 repository listed
-
9 Feb 2024 1 repository listed
-
8 Feb 2024 1 repository listed
-
3 Feb 2024 1 repository listed
-
23 Jan 2024 1 repository listed
-
21 Jan 2024 1 repository listed
-
5 Jan 2024 1 repository listed
-
26 Dec 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
20 Dec 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
19 Dec 2023 1 repository listed
-
15 Dec 2023 1 repository listed
-
11 Dec 2023 1 repository listed
-
3 Dec 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
23 Nov 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
25 Oct 2023 1 repository listed
-
8 Oct 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result (of 3 harvested samples) · 3 pointer-only (licence)
-
1 Oct 2023 1 repository listed
-
21 Sep 2023 1 repository listed
-
24 Aug 2023 1 repository listed
-
21 Aug 2023 1 repository listed
-
17 Aug 2023 1 repository listed
-
29 Jul 2023 1 repository listed
-
19 Jul 2023 1 repository listed
-
14 Jul 2023 1 repository listed
-
12 Jun 2023 1 repository listed
-
3 Jun 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
30 May 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
22 May 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
Syntology lines on 25 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections