Proximal reinforcement learning : efficient off-policy evaluation in partially observed markov decision processes
Year of publication: |
2024
|
---|---|
Authors: | Bennett, Andrew ; Kallus, Nathan |
Published in: |
Operations research. - Linthicum, Md. : INFORMS, ISSN 1526-5463, ZDB-ID 2019440-7. - Vol. 72.2024, 3, p. 1071-1086
|
Subject: | Machine Learning and Data Science | offline reinforcement learning | semiparametric efficiency | unmeasured confounding | Künstliche Intelligenz | Artificial intelligence | Lernen | Learning | Lernprozess | Learning process | Theorie | Theory | Markov-Kette | Markov chain |
-
Kallus, Nathan, (2022)
-
Poisoning finite-horizon Markov decision processes at design time
Caballero, William N., (2021)
-
Learning Markov models via low-rank optimization
Zhu, Ziwei, (2022)
- More ...
-
Questions about questionable research practices in the field of management : a guest commentary
Banks, George C., (2016)
-
Kepes, Sven, (2014)
-
Takin' care of small business : the rise of stakeholder influence
Jimenez, William P., (2021)
- More ...