Offline multi-action policy learning : generalization and optimization
Year of publication: |
2023
|
---|---|
Authors: | Zhou, Zhengyuan ; Athey, Susan ; Wager, Stefan |
Published in: |
Operations research. - Linthicum, Md. : INFORMS, ISSN 1526-5463, ZDB-ID 2019440-7. - Vol. 71.2023, 1, p. 148-183
|
Subject: | Machine Learning and Data Science | minimax regret | data-driven decision making | heterogeneous treatment effects | mixed integer program | policy learning | Künstliche Intelligenz | Artificial intelligence | Lernprozess | Learning process | Theorie | Theory | Entscheidung unter Unsicherheit | Decision under uncertainty | Lernen | Learning | Entscheidung | Decision |
-
Smooth contextual bandits : bridging the parametric and nondifferentiable regret regimes
Hu, Yichun, (2022)
-
Breaking the sample size barrier in model-based reinforcement learning with a generative model
Li, Gen, (2024)
-
Liu, Hongcheng, (2022)
- More ...
-
Policy learning with adaptively collected data
Athey, Susan, (2024)
-
Approximate residual balancing : debiased inference of average treatment effects in high dimensions
Athey, Susan, (2018)
-
Policy Learning With Observational Data
Athey, Susan, (2021)
- More ...