SOTAVerified

Thompson Sampling

Thompson sampling, named after William R. Thompson, is a heuristic for choosing actions that addresses the exploration-exploitation dilemma in the multi-armed bandit problem. It consists of choosing the action that maximizes the expected reward with respect to a randomly drawn belief.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 376–400 of 655 papers

TitleStatusHype
Accelerating Grasp Exploration by Leveraging Learned Priors—0
Thompson sampling for linear quadratic mean-field teams—0
Multi-Agent Active Search using Realistic Depth-Aware Noise ModelCode0
Asymptotic Convergence of Thompson Sampling—0
Adaptive Combinatorial Allocation—0
Multi-armed Bandits with Cost Subsidy—0
Greedy k-Center from Noisy Distance Samples—0
Screening for an Infectious Disease as a Problem in Stochastic Control—0
Bandit Policies for Reliable Cellular Network Handovers in Extreme Mobility—0
Sub-sampling for Efficient Non-Parametric Bandit ExplorationCode0
Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration—0
Bayesian Algorithms for Decentralized Stochastic BanditsCode0
Federated Bayesian Optimization via Thompson SamplingCode1
Reinforcement Learning for Efficient and Tuning-Free Link Adaptation—0
Double-Linear Thompson Sampling for Context-Attentive Bandits—0
Asynchronous ε-Greedy Bayesian OptimisationCode0
Online Learning and Distributed Control for Residential Demand Response—0
Effects of Model Misspecification on Bayesian Bandits: Case Studies in UX Optimization—0
Neural Thompson SamplingCode1
Stage-wise Conservative Linear Bandits—0
Neural Model-based Optimization with Right-Censored Observations—0
Position-Based Multiple-Play Bandits with Thompson Sampling—0
Bandit Change-Point Detection for Real-Time Monitoring High-Dimensional Data Under Sampling Control—0
Partially Observable Online Change Detection via Smooth-Sparse Decomposition—0
Bandits Under The Influence (Extended Version)—0
Show:102550
← PrevPage 16 of 27Next →

No leaderboard results yet.