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 441–450 of 655 papers

TitleStatusHype
Multi-armed Bandits with Cost Subsidy—0
Multi-dueling Bandits with Dependent Arms—0
Multi-Task Combinatorial Bandits for Budget Allocation—0
Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses—0
Neural Contextual Bandits Under Delayed Feedback Constraints—0
Neural Dueling Bandits: Preference-Based Optimization with Human Feedback—0
Neural Model-based Optimization with Right-Censored Observations—0
New Insights into Bootstrapping for Bandits—0
No Algorithmic Collusion in Two-Player Blindfolded Game with Thompson Sampling—0
Nonparametric General Reinforcement Learning—0
Show:102550
← PrevPage 45 of 66Next →

No leaderboard results yet.