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 761–770 of 1262 papers

TitleStatusHype
Online Multi-Armed Bandits with Adaptive Inference—0
Combinatorial Bandits under Strategic ManipulationsCode0
Output-Weighted Sampling for Multi-Armed Bandits with Extreme PayoffsCode0
Top-k eXtreme Contextual Bandits with Arm HierarchyCode0
Meta-Thompson Sampling—0
Player Modeling via Multi-Armed Bandits—0
Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach—0
Multi-Agent Multi-Armed Bandits with Limited Communication—0
Regression Oracles and Exploration Strategies for Short-Horizon Multi-Armed Bandits—0
Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap—0
Show:102550
← PrevPage 77 of 127Next →

Benchmark Results

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