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 626–650 of 655 papers

TitleStatusHype
Incentivizing Exploration In Reinforcement Learning With Deep Predictive ModelsCode0
Bootstrapped Thompson Sampling and Deep Exploration—0
On the Prior Sensitivity of Thompson Sampling—0
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple PlaysCode0
Belief Flows of Robust Online Learning—0
Thompson Sampling for Budgeted Multi-armed Bandits—0
Evaluation of Explore-Exploit Policies in Multi-result Ranking Systems—0
A Note on Information-Directed Sampling and Thompson Sampling—0
Bandit Convex Optimization: sqrtT Regret in One Dimension—0
Thompson sampling with the online bootstrap—0
Freshness-Aware Thompson Sampling—0
Towards Optimal Algorithms for Prediction with Expert Advice—0
Thompson Sampling for Learning Parameterized Markov Decision Processes—0
Efficient Learning in Large-Scale Combinatorial Semi-Bandits—0
An Information-Theoretic Analysis of Thompson Sampling—0
Better Optimism By Bayes: Adaptive Planning with Rich Models—0
Eluder Dimension and the Sample Complexity of Optimistic Exploration—0
Bayesian Mixture Modelling and Inference based Thompson Sampling in Monte-Carlo Tree Search—0
Thompson Sampling for Complex Bandit Problems—0
Thompson Sampling for Online Learning with Linear Experts—0
Generalized Thompson Sampling for Contextual Bandits—0
Thompson Sampling in Dynamic Systems for Contextual Bandit Problems—0
Thompson Sampling for 1-Dimensional Exponential Family Bandits—0
Cover Tree Bayesian Reinforcement Learning—0
Prior-free and prior-dependent regret bounds for Thompson Sampling—0
Show:102550
← PrevPage 26 of 27Next →

No leaderboard results yet.