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 176–200 of 655 papers

TitleStatusHype
Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems—0
Aligning AI Agents via Information-Directed Sampling—0
Differentially Private Federated Bayesian Optimization with Distributed Exploration—0
Delay-Adaptive Learning in Generalized Linear Contextual Bandits—0
Deep Hierarchy in Bandits—0
Deep Contextual Multi-armed Bandits—0
Asynchronous Multi Agent Active Search—0
Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization—0
Adaptive Combinatorial Allocation—0
A Change-Detection Based Thompson Sampling Framework for Non-Stationary Bandits—0
A Batched Multi-Armed Bandit Approach to News Headline Testing—0
Deep Active Ensemble Sampling For Image Classification—0
Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine—0
Deciding What to Learn: A Rate-Distortion Approach—0
Decentralized Multi-Agent Active Search and Tracking when Targets Outnumber Agents—0
Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits—0
Aging Bandits: Regret Analysis and Order-Optimal Learning Algorithm for Wireless Networks with Stochastic Arrivals—0
Debiasing Samples from Online Learning Using Bootstrap—0
Deep Exploration for Recommendation Systems—0
Asymptotic Convergence of Thompson Sampling—0
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models—0
Cover Tree Bayesian Reinforcement Learning—0
The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models—0
A General Recipe for the Analysis of Randomized Multi-Armed Bandit Algorithms—0
Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits—0
Show:102550
← PrevPage 8 of 27Next →

No leaderboard results yet.