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 1131–1140 of 1262 papers

TitleStatusHype
Balanced off-policy evaluation in general action spaces—0
Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards—0
Ballooning Multi-Armed Bandits—0
Bandit Algorithms for Prophet Inequality and Pandora's Box—0
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits—0
BanditMF: Multi-Armed Bandit Based Matrix Factorization Recommender System—0
BanditQ: Fair Bandits with Guaranteed Rewards—0
BanditRank: Learning to Rank Using Contextual Bandits—0
Bandit Regret Scaling with the Effective Loss Range—0
Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits—0
Show:102550
← PrevPage 114 of 127Next →

Benchmark Results

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