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 351–375 of 1262 papers

TitleStatusHype
Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems—0
Contextual Bandits and Imitation Learning via Preference-Based Active Queries—0
Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms—0
Decentralized Smart Charging of Large-Scale EVs using Adaptive Multi-Agent Multi-Armed Bandits—0
VITS : Variational Inference Thompson Sampling for contextual banditsCode0
Adaptive Linear Estimating EquationsCode0
On Interpolating Experts and Multi-Armed Bandits—0
Tracking Most Significant Shifts in Nonparametric Contextual Bandits—0
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features—0
BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits—0
Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization—0
Meta-Learning Adversarial Bandit Algorithms—0
Thompson sampling for improved exploration in GFlowNets—0
Kernel ε-Greedy for Multi-Armed Bandits with Covariates—0
Pure exploration in multi-armed bandits with low rank structure using oblivious sampler—0
You Can Trade Your Experience in Distributed Multi-Agent Multi-Armed Bandits—0
Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning—0
Multi-Fidelity Multi-Armed Bandits Revisited—0
Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits—0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity—0
Federated Linear Contextual Bandits with User-level Differential Privacy—0
Tight Regret Bounds for Single-pass Streaming Multi-armed BanditsCode0
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards—0
Representation-Driven Reinforcement Learning—0
Show:102550
← PrevPage 15 of 51Next →

Benchmark Results

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