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

Standard reinforcement learning (RL) aims to find an optimal policy thatidentifies the best action for each state. However, in healthcare settings,many actions may be near-equivalent with respect to the reward (e.g.,survival). We consider an alternative objective -- learning set-valued policiesto capture near-equivalent actions that lead to similar cumulative rewards. Wepropose a model-free algorithm based on temporal difference learning and anear-greedy heuristic for action selection. We analyze the theoreticalproperties of the proposed algorithm, providing optimality guarantees anddemonstrate our approach on simulated environments and a real clinical task.Empirically, the proposed algorithm exhibits good convergence properties anddiscovers meaningful near-equivalent actions. Our work provides theoretical, aswell as practical, foundations for clinician/human-in-the-loop decision making,in which humans (e.g., clinicians, patients) can incorporate additionalknowledge (e.g., side effects, patient preference) when selecting amongnear-equivalent actions.

Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies