Wesley Cowan

Available identifiers

zbMath Open cowan.wesleyMaRDI QIDQ3300063

List of research outcomes

Publication	Date of Publication	Type
Optimal activation of halting multi‐armed bandit models	2023-10-25	Paper
Exploration-exploitation policies with almost sure, arbitrarily slow growing asymptotic regret	2022-04-14	Paper
Reinforcement learning: a comparison of UCB versus alternative adaptive policies	2020-07-27	Paper
Normal bandits of unknown means and variances	2018-11-22	Paper
Multi-armed bandits under general depreciation and commitment	2017-09-19	Paper

Research outcomes over time

This page was built for person: Wesley Cowan