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
Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference—0
Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure—0
Tight Gap-Dependent Memory-Regret Trade-Off for Single-Pass Streaming Stochastic Multi-Armed Bandits—0
Semi-Parametric Batched Global Multi-Armed Bandits with Covariates—0
Towards Understanding the Benefit of Multitask Representation Learning in Decision Process—0
Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits—0
Functional multi-armed bandit and the best function identification problems—0
Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal TransportabilityCode0
Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models—0
Heterogeneous Multi-Agent Bandits with Parsimonious Hints—0
Show:102550
← PrevPage 6 of 127Next →

Benchmark Results

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