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 691–700 of 1262 papers

TitleStatusHype
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination—0
Dueling Bandits with Adversarial Sleeping—0
Restless and Uncertain: Robust Policies for Restless Bandits via Deep Multi-Agent Reinforcement Learning—0
Bayesian decision-making under misspecified priors with applications to meta-learning—0
Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit—0
Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits—0
Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributions—0
Random Effect Bandits—0
Q-Learning Lagrange Policies for Multi-Action Restless BanditsCode0
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning—0
Show:102550
← PrevPage 70 of 127Next →

Benchmark Results

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