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 61–70 of 655 papers

TitleStatusHype
Batched Bayesian optimization by maximizing the probability of including the optimumCode1
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling ParadoxCode0
Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling—0
Improving Portfolio Optimization Results with Bandit NetworksCode0
Partially Observable Contextual Bandits with Linear Payoffs—0
Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysis—0
Sliding-Window Thompson Sampling for Non-Stationary Settings—0
Multi-Task Combinatorial Bandits for Budget Allocation—0
An Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders—0
Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits—0
Show:102550
← PrevPage 7 of 66Next →

No leaderboard results yet.