English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Interpretable policy learning seeks to estimate intelligible decisionpolicies from observed actions; however, existing models fall short by forcinga tradeoff between accuracy and interpretability. This tradeoff limitsdata-driven interpretations of human decision-making process. e.g. to auditmedical decisions for biases and suboptimal practices, we require models ofdecision processes which provide concise descriptions of complex behaviors.Fundamentally, existing approaches are burdened by this tradeoff because theyrepresent the underlying decision process as a universal policy, when in facthuman decisions are dynamic and can change drastically with contextualinformation. Thus, we propose Contextualized Policy Recovery (CPR), whichre-frames the problem of modeling complex decision processes as a multi-tasklearning problem in which complex decision policies are comprised ofcontext-specific policies. CPR models each context-specific policy as a linearobservation-to-action mapping, and generates new decision models$\textit{on-demand}$ as contexts are updated with new observations. CPR iscompatible with fully offline and partially observable decision environments,and can be tailored to incorporate any recurrent black-box model orinterpretable decision model. We assess CPR through studies on simulated andreal data, achieving state-of-the-art performance on the canonical tasks ofpredicting antibiotic prescription in intensive care units ($+22\%$ AUROC vs.previous SOTA) and predicting MRI prescription for Alzheimer's patients($+7.7\%$ AUROC vs. previous SOTA). With this improvement in predictiveperformance, CPR closes the accuracy gap between interpretable and black-boxmethods for policy learning, allowing high-resolution exploration and analysisof context-specific decision models.

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