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 251–300 of 655 papers

TitleStatusHype
From Predictions to Decisions: The Importance of Joint Predictive Distributions—0
Evaluation of Explore-Exploit Policies in Multi-result Ranking Systems—0
Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space—0
Expected Improvement-based Contextual Bandits—0
Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation—0
An Information-Theoretic Analysis of Thompson Sampling—0
Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits—0
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning—0
An Information-Theoretic Analysis for Thompson Sampling with Many Actions—0
Adaptively Learning to Select-Rank in Online Platforms—0
Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation—0
Incentivized Exploration for Multi-Armed Bandits under Reward Drift—0
Online Learning with Cumulative Oversampling: Application to Budgeted Influence Maximization—0
Bayesian Optimization-Based Beam Alignment for MmWave MIMO Communication Systems—0
A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification—0
Feel-Good Thompson Sampling for Contextual Dueling Bandits—0
Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?—0
Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits—0
First-Order Bayesian Regret Analysis of Thompson Sampling—0
Fixed-Confidence Guarantees for Bayesian Best-Arm Identification—0
Fourier Representations for Black-Box Optimization over Categorical Variables—0
Freshness-Aware Thompson Sampling—0
From Bandits Model to Deep Deterministic Policy Gradient, Reinforcement Learning with Contextual Information—0
Fully Distributed Bayesian Optimization with Stochastic Policies—0
Gaussian Process Thompson Sampling via Rootfinding—0
Generalized Bayesian deep reinforcement learning—0
Generalized Probabilistic Bisection for Stochastic Root-Finding—0
Generalized Regret Analysis of Thompson Sampling using Fractional Posteriors—0
Generalized Thompson Sampling for Contextual Bandits—0
Best Arm Identification in Batched Multi-armed Bandit Problems—0
Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions—0
Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits—0
Graph Neural Thompson Sampling—0
Feedback graph regret bounds for Thompson Sampling and UCB—0
Greedy Bandits with Sampled Context—0
Greedy k-Center from Noisy Distance Samples—0
GuideBoot: Guided Bootstrap for Deep Contextual Bandits—0
GUTS: Generalized Uncertainty-Aware Thompson Sampling for Multi-Agent Active Search—0
gym-saturation: Gymnasium environments for saturation provers (System description)—0
Hierarchical Bayesian Bandits—0
High-dimensional near-optimal experiment design for drug discovery via Bayesian sparse sampling—0
Horde of Bandits using Gaussian Markov Random Fields—0
Human collective intelligence as distributed Bayesian inference—0
Hypermodels for Exploration—0
IBAC: An Intelligent Dynamic Bandwidth Channel Access Avoiding Outside Warning Range Problem—0
Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning—0
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems—0
Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration—0
Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems—0
Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network—0
Show:102550
← PrevPage 6 of 14Next →

No leaderboard results yet.