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 931–940 of 1262 papers

TitleStatusHype
Generalizable Meta-Heuristic based on Temporal Estimation of Rewards for Large Scale Blackbox Optimization—0
Online Fair Division with Contextual Bandits—0
Online Fair Revenue Maximizing Cake Division with Non-Contiguous Pieces in Adversarial Bandits—0
Online Learning for Autonomous Management of Intent-based 6G Networks—0
Online Learning for Cooperative Multi-Player Multi-Armed Bandits—0
Online Learning in Contextual Bandits using Gated Linear Networks—0
Online learning over a finite action set with limited switching—0
Online Learning under Adversarial Corruptions—0
Online Learning via the Differential Privacy Lens—0
Online Learning with an Unknown Fairness Metric—0
Show:102550
← PrevPage 94 of 127Next →

Benchmark Results

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