Joint Econometrics and Statistics Workshop
Super Reinforcement Learning in Confounded Environments
Jiay Wang (University of Texas)
Friday 03 February 2023 12:00 - 13:00
Many of our seminars and public events this year will continue as in person or as hybrid (online and in person) events. Please check our website listings and Twitter feed @STICERD_LSE for updates.
Unless otherwise specified, in-person seminars are open to the public.
Those unable to join the seminars in-person are welcome to participate via zoom if the event is hybrid.
About this event
We introduce super reinforcement learning in the batch setting, which takes the observed action as input for achieving a stronger oracle in policy learning. In the presence of unmeasured confounders, the recommendations from human agents recorded in the observed data allow us to recover certain unobserved information. Including this information in the policy search, the proposed super reinforcement learning will yield a super-policy that is guaranteed to outperform both the standard optimal policy and the behavior one (e.g., human agents' recommendations). Furthermore, to address the issue of unmeasured confounding in finding super-policies, a number of non-parametric identification results are established. Based on these identification results, we develop several super-policy learning algorithms and derive their corresponding finite-sample regret guarantees. Finally, we illustrate the superior performance of our proposal through extensive simulations and two real datasets related to improving the health policy.
Econometrics and Statistics seminars are held on Fridays in term time at 12:00-13:00, ONLINE, unless specified otherwise.
Seminar organisers: Dr Tatiana Komarova and Dr Yunxiao Chen.
For further information please contact Lubala Chibwe: email@example.com.
Please use this link to subscribe or unsubscribe to the Econometrics and Statistics seminars mailing list (stats).