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 321–330 of 1262 papers

TitleStatusHype
Best Arm Identification with Fixed Budget: A Large Deviation PerspectiveCode0
Observation-Augmented Contextual Multi-Armed Bandits for Robotic Search and Exploration—0
Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints—0
Risk-Aware Continuous Control with Neural Contextual BanditsCode0
A Hierarchical Nearest Neighbour Approach to Contextual Bandits—0
Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents—0
Contextual Bandits with Online Neural Regression—0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Distributed Optimization via Kernelized Multi-armed Bandits—0
Marginal Density Ratio for Off-Policy Evaluation in Contextual BanditsCode0
Show:102550
← PrevPage 33 of 127Next →

Benchmark Results

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