D'un dualisme bien utile

MULTI-MODAL UTILE DISTINCTIONS Multi-Modal Utile Distinctions

We introduce Multi-Modal Utility Trees (MMU), an algorithm for autonomously learning decision treebased state abstractions in Partially Observable Markov Decision Processes with multi-modal observations. MMU builds the trees using the Kolmogorov-Smirnov statistical test. Additionally, MMU incorporates the ability to perform online tree restructuring, enabling it to build and maintain a compact ...

El Bien Moral

Biblio Bien vieillir nov 2006

Utile or futile: biomarkers in the ICU

Biomarkers complement other clinical information by proving quantitative data regarding a pathophysiological mechanism that can be used for the early diagnosis of a specific disease, to monitor and guide treatment, and to predict the risk of death or other adverse events. The stronger the link between the information provided by the biomarker and the immediate clinical course of action that we ...

Utile Distinctions for Relational Reinforcement Learning

We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-based function approximation derived from McCallum’s [1995] UTree algorithm. We have extended this approach to use a relational representation where relational observations are represented by attributed graphs [McGovern...