Towards machines that understand people

Andrew Howes, Jussi P. P. Jokinen, A Oulasvirta

Research output: Contribution to journalArticleScientificpeer-review

3 Citations (Scopus)
40 Downloads (Pure)

Abstract

The ability to estimate the state of a human partner is an insufficient basis on which to build cooperative agents. Also needed is an ability to predict how people adapt their behavior in response to an agent's actions. We propose a new approach based on computational rationality, which models humans based on the idea that predictions can be derived by calculating policies that are approximately optimal given human-like bounds. Computational rationality brings together reinforcement learning and cognitive modeling in pursuit of this goal, facilitating machine understanding of humans.
Original languageEnglish
Pages (from-to)312-327
Number of pages16
JournalAI Magazine
Volume44
Issue number3
DOIs
Publication statusPublished - 4 Sept 2023
MoE publication typeA1 Journal article-refereed

Fingerprint

Dive into the research topics of 'Towards machines that understand people'. Together they form a unique fingerprint.

Cite this