KIT | KIT-Bibliothek | Impressum | Datenschutz

Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning

Deuschel, Jannik; Ellington, Caleb N.; Lengerich, Benjamin J.; Luo, Yingtao; Friederich, Pascal ORCID iD icon 1; Xing, Eric P.
1 Institut für Theoretische Informatik (ITI), Karlsruher Institut für Technologie (KIT)

Abstract:

Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models fall short by forcing a tradeoff between accuracy and interpretability. This tradeoff limits data-driven interpretations of human decision-making process. e.g. to audit medical decisions for biases and suboptimal practices, we require models of decision processes which provide concise descriptions of complex behaviors. Fundamentally, existing approaches are burdened by this tradeoff because they represent the underlying decision process as a universal policy, when in fact human decisions are dynamic and can change drastically with contextual information. Thus, we propose Contextualized Policy Recovery (CPR), which re-frames the problem of modeling complex decision processes as a multi-task learning problem in which complex decision policies are comprised of context-specific policies. CPR models each context-specific policy as a linear observation-to-action mapping, and generates new decision models $\textit{on-demand}$ as contexts are updated with new observations. CPR is compatible with fully offline and partially observable decision environments, and can be tailored to incorporate any recurrent black-box model or interpretable decision model. ... mehr


Volltext §
DOI: 10.5445/IR/1000165104
Veröffentlicht am 30.11.2023
Originalveröffentlichung
DOI: 10.48550/arXiv.2310.07918
Dimensions
Zitationen: 1
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Theoretische Informatik (ITI)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2023
Sprache Englisch
Identifikator KITopen-ID: 1000165104
HGF-Programm 43.31.01 (POF IV, LK 01) Multifunctionality Molecular Design & Material Architecture
Verlag arxiv
Vorab online veröffentlicht am 11.10.2023
Schlagwörter Machine Learning (cs.LG), Artificial Intelligence (cs.AI), Machine Learning (stat.ML)
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page