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 611–620 of 1262 papers

TitleStatusHype
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
Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits—0
Contextual Bandits with Similarity Information—0
Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions—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
Improving Offline Contextual Bandits with Distributional Robustness—0
Show:102550
← PrevPage 62 of 127Next →

Benchmark Results

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