Counterfactuals in Minds and Machines

Descripción del proyecto

Avanzar en el apoyo a la toma de decisiones mediante el razonamiento contrafactual

Los seres humanos destacan en el razonamiento contrafactual, imaginando pasados alternativos para evaluar lo que podría haber sido mejor o peor. Esta capacidad desempeña un papel fundamental a la hora de aprender de experiencias limitadas y mejorar la toma de decisiones. Sin embargo, a pesar del creciente papel del aprendizaje automático en el apoyo a la toma de decisiones en campos como la medicina y la educación, con la mayoría de los algoritmos se han tenido dificultades para incorporar este tipo de razonamiento. Teniendo esto en cuenta, el equipo del proyecto COUNTERFACT, financiado por el CEI, pretende colmar esta laguna desarrollando modelos de aprendizaje automático capaces de realizar razonamientos contrafactuales. Estos modelos potenciarán los sistemas de apoyo a la toma de decisiones, mejorarán la toma de decisiones humana y reducirán las exigencias informáticas y de datos, al tiempo que ayudarán a las personas a aprender de las elecciones pasadas para lograr mejores resultados.

Objetivo

Reasoning about what might have been, about alternatives to our own pasts, is a landmark of human intelligence. Such type of reasoning, called counterfactual reasoning, is often evaluative, specifying alternatives that are in some sense better or worse than our past reality, and has been shown to play a significant role in the ability that humans have to learn from limited past experience and improve their decision making skills over time.

In recent years, there has been an increasing excitement on the potential of machine learning models and algorithms to support human decision making in a variety of high-stakes domains such as medicine, education or science. However, these models and algorithms have been traditionally unable to perform, nor benefit from, counterfactual reasoning. In this project, our goal is to bridge this gap.

We will develop machine learning models and algorithms for automated decision support that are able to perform and benefit from counterfactual reasoning in multiple ways. For example, they will perform counterfactual reasoning about human behavior to anticipate how humans incorporate algorithmic advice into their decisions. This will enable a new generation of decision support systems that can only increase and never decrease the average quality of human decisions. Moreover, they will use the structural similarities and shared properties across different counterfactual decision making scenarios to significantly reduce their computational and data requirements. In addition, these models and algorithms will also help humans learn from their own past decisions by identifying alternative decisions that would have led to better outcomes. Finally, we will perform large-scale human subject studies with both laypersons and experts to evaluate their effectiveness in a wide variety of decision making tasks.