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 451–500 of 655 papers

TitleStatusHype
Thompson Sampling Achieves O(T) Regret in Linear Quadratic Control—0
Thompson Sampling with Approximate Inference—0
Thompson Sampling and Approximate Inference—0
Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes—0
Thompson Sampling for 1-Dimensional Exponential Family Bandits—0
Thompson Sampling for Adversarial Bit Prediction—0
Thompson Sampling for Bandits with Clustered Arms—0
Thompson Sampling for Budgeted Multi-armed Bandits—0
Thompson Sampling Algorithms for Cascading Bandits—0
Thompson Sampling for Combinatorial Network Optimization in Unknown Environments—0
Thompson Sampling for (Combinatorial) Pure Exploration—0
Thompson Sampling for Combinatorial Semi-Bandits—0
Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints—0
Thompson Sampling for Complex Bandit Problems—0
Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints—0
Thompson Sampling for Dynamic Pricing—0
Thompson Sampling for Gaussian Entropic Risk Bandits—0
Thompson sampling for improved exploration in GFlowNets—0
Thompson Sampling for Infinite-Horizon Discounted Decision Processes—0
Thompson Sampling for Learning Parameterized Markov Decision Processes—0
Thompson Sampling for Linear Bandit Problems with Normal-Gamma Priors—0
Thompson Sampling for Linear-Quadratic Control Problems—0
Thompson sampling for linear quadratic mean-field teams—0
Thompson Sampling for Noncompliant Bandits—0
Thompson Sampling for Online Learning with Linear Experts—0
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions—0
Thompson Sampling for Pursuit-Evasion Problems—0
Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit—0
Thompson Sampling For Stochastic Bandits with Graph Feedback—0
Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis—0
Thompson Sampling for the MNL-Bandit—0
Thompson Sampling for Unimodal Bandits—0
Thompson Sampling for Unsupervised Sequential Selection—0
Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study—0
Thompson Sampling Guided Stochastic Searching on the Line for Deceptive Environments with Applications to Root-Finding Problems—0
Thompson Sampling in Dynamic Systems for Contextual Bandit Problems—0
Thompson Sampling in Non-Episodic Restless Bandits—0
Thompson Sampling in Online RLHF with General Function Approximation—0
Thompson Sampling in Partially Observable Contextual Bandits—0
Thompson Sampling is Asymptotically Optimal in General Environments—0
Thompson Sampling Itself is Differentially Private—0
Thompson Sampling-like Algorithms for Stochastic Rising Bandits—0
Thompson Sampling on Asymmetric α-Stable Bandits—0
Thompson Sampling on Symmetric α-Stable Bandits—0
Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards—0
Thompson Sampling under Bernoulli Rewards with Local Differential Privacy—0
Thompson Sampling with a Mixture Prior—0
Thompson Sampling with Diffusion Generative Prior—0
Thompson sampling with the online bootstrap—0
Thompson Sampling with Unrestricted Delays—0
Show:102550
← PrevPage 10 of 14Next →

No leaderboard results yet.