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 71–80 of 1262 papers

TitleStatusHype
Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits—0
Quantile Multi-Armed Bandits with 1-bit Feedback—0
Towards a Sharp Analysis of Offline Policy Learning for f-Divergence-Regularized Contextual Bandits—0
From Restless to Contextual: A Thresholding Bandit Approach to Improve Finite-horizon PerformanceCode0
Nearly Tight Bounds for Cross-Learning Contextual Bandits with Graphical Feedback—0
Early Stopping in Contextual Bandits and Inferences—0
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards—0
Optimizing Online Advertising with Multi-Armed Bandits: Mitigating the Cold Start Problem under Auction Dynamics—0
Nearly Tight Bounds for Exploration in Streaming Multi-armed Bandits with Known Optimality Gap—0
Meta-Prompt Optimization for LLM-Based Sequential Decision Making—0
Show:102550
← PrevPage 8 of 127Next →

Benchmark Results

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