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

The potential of Reinforcement Learning (RL) has been demonstrated throughsuccessful applications to games such as Go and Atari. However, while it isstraightforward to evaluate the performance of an RL algorithm in a gamesetting by simply using it to play the game, evaluation is a major challenge inclinical settings where it could be unsafe to follow RL policies in practice.Thus, understanding sensitivity of RL policies to the host of decisions madeduring implementation is an important step toward building the type of trust inRL required for eventual clinical uptake. In this work, we perform asensitivity analysis on a state-of-the-art RL algorithm (Dueling Double DeepQ-Networks)applied to hemodynamic stabilization treatment strategies for septicpatients in the ICU. We consider sensitivity of learned policies to inputfeatures, embedding model architecture, time discretization, reward function,and random seeds. We find that varying these settings can significantly impactlearned policies, which suggests a need for caution when interpreting RL agentoutput.

Is Deep Reinforcement Learning Ready for Practical Applications in  Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in  Sepsis Patients