UCB Algorithms
UCB: Upper Confidence Bound
Overview
UCB algorithms choose actions by combining estimated rewards with confidence bonuses, balancing exploration of uncertain options against exploiting promising ones. The approach spans multi-armed and linear or contextual bandits, as well as Gaussian-process optimization, with variants for nonstationary rewards, constraints, delayed feedback, and multiple objectives. Analyses typically establish regret guarantees, while benchmarks test performance in settings such as pricing, ranking, resource allocation, and adaptive model selection. A central challenge is adapting confidence bounds to realistic noise and structure without making decisions too costly or compromising safety, fairness, or valid statistical inference.
Latest papers
62 papers5 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.