Showing 1 - 6 of 6
Persistent link: https://www.econbiz.de/10001251104
Persistent link: https://www.econbiz.de/10009126854
Persistent link: https://www.econbiz.de/10010347832
Persistent link: https://www.econbiz.de/10003362955
This paper revisits a recent study by Posen and Levinthal (2012) on the exploration/exploitation tradeoff for a multi-armed bandit problem, where the reward probabilities undergo random shocks. We show that their analysis suffers two shortcomings: it assumes that learning is based on stale...
Persistent link: https://www.econbiz.de/10013076288
Persistent link: https://www.econbiz.de/10009792417