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 581–590 of 1262 papers

TitleStatusHype
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits—0
Improving Fairness in Adaptive Social Exergames via Shapley Bandits—0
Improving Offline Contextual Bandits with Distributional Robustness—0
Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions—0
Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits—0
Incentivising Exploration and Recommendations for Contextual Bandits with Payments—0
Incentivized Exploration for Multi-Armed Bandits under Reward Drift—0
Incentivized Exploration via Filtered Posterior Sampling—0
Indexability and Rollout Policy for Multi-State Partially Observable Restless Bandits—0
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses—0
Show:102550
← PrevPage 59 of 127Next →

Benchmark Results

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