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 951–960 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
Show:102550
← PrevPage 96 of 127Next →

Benchmark Results

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