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 1001–1010 of 1262 papers

TitleStatusHype
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewardsCode0
Model selection for contextual banditsCode0
Equipping Experts/Bandits with Long-term Memory—0
Rarely-switching linear bandits: optimization of causal effects for the real world—0
Multi-Objective Generalized Linear Bandits—0
Distribution-dependent and Time-uniform Bounds for Piecewise i.i.d Bandits—0
Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?—0
Regret Bounds for Thompson Sampling in Episodic Restless Bandit ProblemsCode0
Top-k Combinatorial Bandits with Full-Bandit Feedback—0
Are sample means in multi-armed bandits positively or negatively biased?—0
Show:102550
← PrevPage 101 of 127Next →

Benchmark Results

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