SOTAVerified

Multi-Armed Bandits

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 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 911–920 of 1262 papers

TitleStatusHype
Decentralized Multi-player Multi-armed Bandits with No Collision Information—0
Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions—0
Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis—0
Bandit Learning with Delayed Impact of Actions—0
The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many ArmsCode0
Survey Bandits with Regret Guarantees—0
Online Learning in Contextual Bandits using Gated Linear Networks—0
Residual Bootstrap Exploration for Bandit Algorithms—0
On conditional versus marginal bias in multi-armed bandits—0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Show:102550
← PrevPage 92 of 127Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NeuralLinear FullPosterior-MRCumulative regret1.92—Unverified
2Linear FullPosterior-MRCumulative regret1.82—Unverified