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 251–275 of 655 papers

TitleStatusHype
Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs—0
Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes—0
Thompson Sampling for (Combinatorial) Pure Exploration—0
Thompson Sampling for Robust Transfer in Multi-Task BanditsCode0
Thompson Sampling Achieves O(T) Regret in Linear Quadratic Control—0
A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification—0
On Provably Robust Meta-Bayesian OptimizationCode0
Top Two Algorithms Revisited—0
Regret Bounds for Information-Directed Reinforcement Learning—0
A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits—0
Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits—0
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization—0
Incentivizing Combinatorial Bandit Exploration—0
Mixed-Effect Thompson SamplingCode0
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits—0
Surrogate modeling for Bayesian optimization beyond a single Gaussian process—0
Information-Directed Selection for Top-Two AlgorithmsCode0
Fast Change Identification in Multi-Play Bandits and its Applications in Wireless Networks—0
Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization—0
Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization—0
Non-Stationary Bandit Learning via Predictive Sampling—0
Evolutionary Multi-Armed Bandits with Genetic Thompson SamplingCode0
Thompson Sampling for Bandit Learning in Matching MarketsCode0
On Kernelized Multi-Armed Bandits with Constraints—0
Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic maskingCode0
Show:102550
← PrevPage 11 of 27Next →

No leaderboard results yet.