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 351–360 of 655 papers

TitleStatusHype
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits—0
Optimal Learning for Dynamic Coding in Deadline-Constrained Multi-Channel Networks—0
Optimal No-regret Learning in Repeated First-price Auctions—0
Optimal Recommendation to Users that React: Online Learning for a Class of POMDPs—0
Optimistic posterior sampling for reinforcement learning: worst-case regret bounds—0
Optimistic Thompson Sampling for No-Regret Learning in Unknown Games—0
Optimization of a SSP's Header Bidding Strategy using Thompson Sampling—0
Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification—0
Ordinal Bayesian Optimisation—0
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space—0
Show:102550
← PrevPage 36 of 66Next →

No leaderboard results yet.