Ambiguous dynamic treatment regimes : a reinforcement learning approach
Year of publication: |
2021 ; Version: December 8, 2021
|
---|---|
Authors: | Saghafian, Soroush |
Publisher: |
[Cambridge, MA] : Harvard Kennedy School, John F. Kennedy School of Government |
Subject: | Observational Data | Dynamic Treatment Regimes | Unobserved Confounders | APOMDPs | Ambiguous Partially Observable Mark Decision Processes | Reinforcement Learning | Theorie | Theory | Lernprozess | Learning process | Lernen | Learning | Entscheidung unter Unsicherheit | Decision under uncertainty |
Extent: | 1 Online-Ressource (circa 36 Seiten) Illustrationen |
---|---|
Series: | Faculty research working paper series / John F. Kennedy School of Government, Harvard University. - Cambridge, Mass., ZDB-ID 2123740-2. - Vol. RWP21, 034 (December 2021) |
Type of publication: | Book / Working Paper |
Type of publication (narrower categories): | Graue Literatur ; Non-commercial literature ; Arbeitspapier ; Working Paper |
Language: | English |
Other identifiers: | 10.2139/ssrn.3980837 [DOI] |
Source: | ECONIS - Online Catalogue of the ZBW |
-
Optimistic posterior sampling for reinforcement learning : worst-case regret bounds
Agrawal, Shipra, (2023)
-
Our (represented) world : a quantum-like object
Lambert-Mogiliansky, Ariane, (2015)
-
Uncertainty, imperfect information, and learning in the international market (revised)
Chen, Cheng, (2018)
- More ...
-
Patient streaming as a mechanism for improving responsiveness in emergency departments
Hopp, Wallace J., (2012)
-
Li, Xiang, (2013)
-
Kim, Eungab, (2013)
- More ...