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 601–625 of 1262 papers

TitleStatusHype
Instance-optimal PAC Algorithms for Contextual Bandits—0
Concentrated Differential Privacy for Bandits—0
Contextual Bandits with Stage-wise Constraints—0
A General Theory of the Stochastic Linear Bandit and Its Applications—0
Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems—0
Contextual Bandits with Sparse Data in Web setting—0
Incentivized Exploration via Filtered Posterior Sampling—0
Incentivized Exploration for Multi-Armed Bandits under Reward Drift—0
BanditMF: Multi-Armed Bandit Based Matrix Factorization Recommender System—0
Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement—0
Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?—0
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon—0
Joint Representation Training in Sequential Tasks with Shared Structure—0
Incentivising Exploration and Recommendations for Contextual Bandits with Payments—0
Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits—0
Contextual Bandits with Similarity Information—0
Kernel ε-Greedy for Multi-Armed Bandits with Covariates—0
Kernel Methods for Cooperative Multi-Agent Contextual Bandits—0
KL-regularization Itself is Differentially Private in Bandits and RLHF—0
Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits—0
Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions—0
Lagrangian Index Policy for Restless Bandits with Average Reward—0
Improving Offline Contextual Bandits with Distributional Robustness—0
Contextual Bandits with Side-Observations—0
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits—0
Show:102550
← PrevPage 25 of 51Next →

Benchmark Results

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