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 51–60 of 1262 papers

TitleStatusHype
Bandit-Based Monte Carlo Optimization for Nearest NeighborsCode0
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox OptimizationCode0
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous AgentsCode0
Addressing the Long-term Impact of ML Decisions via Policy RegretCode0
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Contextual bandits with entropy-based human feedbackCode0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Adapting multi-armed bandits policies to contextual bandits scenariosCode0
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewardsCode0
Show:102550
← PrevPage 6 of 127Next →

Benchmark Results

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