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 1–10 of 655 papers

TitleStatusHype
Robust Policy Switching for Antifragile Reinforcement Learning for UAV Deconfliction in Adversarial Environments—0
Context Attribution with Multi-Armed Bandit Optimization—0
Adaptive Data Augmentation for Thompson Sampling—0
Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?—0
Efficient kernelized bandit algorithms via exploration distributions—0
Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget—0
Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling—0
Thompson Sampling in Online RLHF with General Function Approximation—0
Stable Thompson Sampling: Valid Inference via Variance Inflation—0
Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection—0
Show:102550
← PrevPage 1 of 66Next →

No leaderboard results yet.