SOURCE-LINKED INTELLIGENCE

Pooling and Drift in Delayed Bandits

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

A system often has to act long before it learns whether the act worked: a recommender sees a click in seconds and a purchase in days. With $K$ actions and a delay of $d$ rounds, the best rate known for this setting is $\widetilde{O}(\sqrt{(K+d)T})$ over $T$ rounds, so a longer menu is always more expensive to learn from. It need not be: if the outcome depends on the action only through the state it produced, then one late outcome informs every action that could have produced the observed state, and the price is set by how many genuinely different states the actions produce rather than by how m

Read original source ↗ Open in workspace

recordType

paper

region

Global