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 951–975 of 1262 papers

TitleStatusHype
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling—0
On Minimax Optimal Offline Policy Evaluation—0
On No-Sensing Adversarial Multi-player Multi-armed Bandits with Collision Communications—0
Towards Tractable Optimism in Model-Based Reinforcement Learning—0
On Penalization in Stochastic Multi-armed Bandits—0
On Private and Robust Bandits—0
On Quantum Natural Policy Gradients—0
On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits—0
On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits—0
On Sequential Elimination Algorithms for Best-Arm Identification in Multi-Armed Bandits—0
On Speeding Up Language Model Evaluation—0
On Submodular Contextual Bandits—0
On the bias, risk and consistency of sample means in multi-armed bandits—0
On the Complexity of Representation Learning in Contextual Linear Bandits—0
On the Identification and Mitigation of Weaknesses in the Knowledge Gradient Policy for Multi-Armed Bandits—0
On the Importance of Uncertainty in Decision-Making with Large Language Models—0
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits—0
Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits—0
On the Problem of Best Arm Retention—0
Contextual Decision-Making with Knapsacks Beyond the Worst Case—0
On The Statistical Complexity of Offline Decision-Making—0
On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs—0
On Universally Optimal Algorithms for A/B Testing—0
Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture—0
Open Problem: Model Selection for Contextual Bandits—0
Show:102550
← PrevPage 39 of 51Next →

Benchmark Results

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