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 631–640 of 1262 papers

TitleStatusHype
Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search—0
Semantic Parsing for Planning Goals as Constrained Combinatorial Contextual Bandits—0
Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version)—0
Modelling Cournot Games as Multi-agent Multi-armed Bandits—0
Off-Policy Evaluation Using Information Borrowing and Context-Based SwitchingCode0
Stochastic differential equations for limiting description of UCB rule for Gaussian multi-armed bandits—0
Safe Linear Leveling Bandits—0
Privacy Amplification via Shuffling for Linear Contextual Bandits—0
Efficient Action Poisoning Attacks on Linear Contextual Bandits—0
Best Arm Identification under Additive Transfer Bandits—0
Show:102550
← PrevPage 64 of 127Next →

Benchmark Results

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