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 821–830 of 1262 papers

TitleStatusHype
CorrAttack: Black-box Adversarial Attack with Structured Search—0
Neural Thompson SamplingCode1
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon—0
Contextual Bandits for adapting to changing User preferences over time—0
Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms—0
Online Semi-Supervised Learning in Contextual Bandits with Episodic RewardCode0
Thompson Sampling for Unsupervised Sequential Selection—0
Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback—0
Deep Contextual Bandits for Fast Initial Access in mmWave Based User-Centric Ultra-Dense Networks—0
Dual-Mandate Patrols: Multi-Armed Bandits for Green SecurityCode0
Show:102550
← PrevPage 83 of 127Next →

Benchmark Results

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