From choice architecture to choice engineering

Dan, Ohad; Loewenstein, Yonatan

doi:10.1038/s41467-019-10825-6

Cited by 9 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This experiment is based on the adversarial bandit task introduced in ref. 1 . On each trial, subjects make choices between two squares, one on the left of the screen and the other on the right.…”

Section: Resultsmentioning

confidence: 99%

“…We generated data from a

-learning algorithm (1,000 learners) with the same parameters used in ref. 1 and used these data to train the learner model. Then we used RL to train the adversary to exploit the learner model.…”

Section: Resultsmentioning

confidence: 99%

“…Doing this efficiently requires a characterization of the processes of human choice that makes good predictions across a wide range of potentially unusual inputs. It therefore constitutes an excellent test of our models of choice ( 1 ). We have recently shown that recurrent neural network (RNN) models provide accurate, flexible, and informative treatments of human decision-making ( 2 – 4 ).…”

mentioning

confidence: 99%

“…This provides the general blueprint to tackling the first question. To show the promise of this framework to surface such vulnerabilities in human subjects, we applied it to three decision-making tasks involving choice engineering ( 1 ), response inhibition ( 8 ), and a social exchange game ( 9 ) and tested the resulting adversaries on volunteers to assess the biases. We show that in all of the tasks the framework was able automatically to specify adversarial inputs which were effective in steering choice processes to favor particular target actions or goals.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Adversarial vulnerabilities of human decision-making

Dezfouli

Nock

Dayan

2020

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Adversarial examples are carefully crafted input patterns that are surprisingly poorly classified by artificial and/or natural neural networks. Here we examine adversarial vulnerabilities in the processes responsible for learning and choice in humans. Building upon recent recurrent neural network models of choice processes, we propose a general framework for generating adversarial opponents that can shape the choices of individuals in particular decision-making tasks toward the behavioral patterns desired by the adversary. We show the efficacy of the framework through three experiments involving action selection, response inhibition, and social decision-making. We further investigate the strategy used by the adversary in order to gain insights into the vulnerabilities of human choice. The framework may find applications across behavioral sciences in helping detect and avoid flawed choice.

show abstract

Section: Resultsmentioning

confidence: 99%

“…We generated data from a

-learning algorithm (1,000 learners) with the same parameters used in ref. 1 and used these data to train the learner model. Then we used RL to train the adversary to exploit the learner model.…”

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Adversarial vulnerabilities of human decision-making

Dezfouli

Nock

Dayan

2020

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…These can be revealing about the structure of the computation and modes of failure. Although it is putatively such adversarial cases that keep industries such as gambling and social media in their cups, systematic investigations in the case of decisionmaking are currently thinner on the ground (Dan and Loewenstein 2019;Dezfouli et al 2020).…”

Section: Ll Open Accessmentioning

confidence: 99%

Computational Psychiatry for Computers

Schulz

Dayan

2020

iScience

View full text Add to dashboard Cite

Computational psychiatry is a nascent field that attempts to use multi-level analyses of the underlying computational problems that we face in navigating a complex, uncertain and changing world to illuminate mental dysfunction and disease. Two particular foci of the field are the costs and benefits of environmental adaptivity and the danger and necessity of heuristics. Here, we examine the extent to which these foci and others can be used to study the actual and potential flaws of the artificial computational devices that we are increasingly inventing and empowering to navigate this very same environment on our behalf.

show abstract