Towards machines that understand people

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

doi:10.1002/aaai.12116

Towards machines that understand people

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

Tutkimustuotos: Lehtiartikkeli › Article › Scientific › vertaisarvioitu

6 Sitaatiot (Scopus)

43 Lataukset (Pure)

Abstrakti

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.

Alkuperäiskieli	Englanti
Sivut	312-327
Sivumäärä	16
Julkaisu	AI Magazine
Vuosikerta	44
Numero	3
DOI - pysyväislinkit	https://doi.org/10.1002/aaai.12116
Tila	Julkaistu - 4 syysk. 2023
OKM-julkaisutyyppi	A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Pääsy asiakirjaan

10.1002/aaai.12116Lisenssi: CC BY

Towards machines that understand peopleFinal published version, 480 KBLisenssi: CC BY

Muut tiedostot ja linkit

FCAI: Suomen tekoälykeskus
Oulasvirta, A. & Jiang, Y.
01/01/2022 → 31/12/2022
Projekti: Academy of Finland: Other research funding
Human Automata: Kollaboratiivisen tekoälyn simulaattorimenetelmät
Oulasvirta, A., Shiripour, M., Putkonen, A., Rastogi, A., Hegemann, L., Iyer, A., Santala, S., Dayama, N., Laine, M., Halasinamara Chandramouli, S., Li, C., Zhu, Y., Kompatscher, J., Liao, Y., Kylmälä, J. & Nioche, A.
01/01/2020 → 31/12/2023
Projekti: Academy of Finland: Other research funding
-: Bayesian Artefact Design
Oulasvirta, A., Shin, J., Hegemann, L., Todi, K., Putkonen, A., Halasinamara Chandramouli, S., Hassinen, H., Dayama, N., Leiva, L., Laine, M., Zhu, Y., Liao, Y., Peng, Z. & Nioche, A.
01/09/2018 → 31/08/2023
Projekti: Academy of Finland: Other research funding

Siteeraa tätä

@article{2fc3edc236614514b953d0971e8f82e7,

title = "Towards machines that understand people",

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.",

author = "Andrew Howes and Jokinen, {Jussi P. P.} and A Oulasvirta",

year = "2023",

month = sep,

day = "4",

doi = "10.1002/aaai.12116",

language = "English",

volume = "44",

pages = "312--327",

journal = "AI Magazine",

issn = "0738-4602",

publisher = "American Association for Artificial Intelligence",

number = "3",

}

TY - JOUR

T1 - Towards machines that understand people

AU - Howes, Andrew

AU - Jokinen, Jussi P. P.

AU - Oulasvirta, A

PY - 2023/9/4

Y1 - 2023/9/4

N2 - 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.

AB - 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.

UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=aalto_pure&SrcAuth=WosAPI&KeyUT=WOS:001058084100001&DestLinkType=FullRecord&DestApp=WOS

UR - http://www.scopus.com/inward/record.url?scp=85181478697&partnerID=8YFLogxK

U2 - 10.1002/aaai.12116

DO - 10.1002/aaai.12116

M3 - Article

SN - 0738-4602

VL - 44

SP - 312

EP - 327

JO - AI Magazine

JF - AI Magazine

IS - 3

ER -

Towards machines that understand people

Abstrakti

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Projektit

FCAI: Suomen tekoälykeskus

Human Automata: Kollaboratiivisen tekoälyn simulaattorimenetelmät

-: Bayesian Artefact Design

Siteeraa tätä