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 511–520 of 1262 papers

TitleStatusHype
Replicable Bandits—0
ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits—0
Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs—0
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits—0
Off-Policy Risk Assessment in Markov Decision Processes—0
Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Bandits—0
Towards Robust Off-Policy Evaluation via Human Inputs—0
Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems—0
Risk-aware linear bandits with convex loss—0
Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits—0
Show:102550
← PrevPage 52 of 127Next →

Benchmark Results

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