Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making

Hüseyin Aydin; Kevin Godin-Dubois; Libio Goncalvez Braz; Floris Den Hengst; Kim Baraka; Mustafa Mert Çelikok; Andreas Sauter; Shihan Wang; Frans A. Oliehoek

doi:10.3233/FAIA250669

Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making

Hüseyin Aydin, Kevin Godin-Dubois, Libio Goncalvez Braz, Floris Den Hengst, Kim Baraka, Mustafa Mert Çelikok, Andreas Sauter, Shihan Wang, Frans A. Oliehoek

Sequential Decision Making

Research output: Contribution to journal › Article › Scientific › peer-review

Abstract

We present SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments), a generic framework to support experiments with RL agents and humans. It consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, and deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide variety of research questions related to the interaction between humans and RL agents and aims to standardize the field of study on RL in human contexts.

Original language	English
Pages (from-to)	486-488
Number of pages	3
Journal	Frontiers in Artificial Intelligence and Applications
Volume	408
DOIs	https://doi.org/10.3233/FAIA250669
Publication status	Published - 2025

Keywords

experimentation
hybrid AI
reinforcement learning
software

Access to Document

10.3233/FAIA250669

FAIA-408-FAIA250669Final published version, 144 KBLicence: CC BY-NC

Cite this

@article{5a5d5012640240fc84cc6ae1fc2c253e,

title = "Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making",

abstract = "We present SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments), a generic framework to support experiments with RL agents and humans. It consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, and deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide variety of research questions related to the interaction between humans and RL agents and aims to standardize the field of study on RL in human contexts.",

keywords = "experimentation, hybrid AI, reinforcement learning, software",

author = "H{\"u}seyin Aydin and Kevin Godin-Dubois and {Goncalvez Braz}, Libio and {Den Hengst}, Floris and Kim Baraka and {\c C}elikok, {Mustafa Mert} and Andreas Sauter and Shihan Wang and Oliehoek, {Frans A.}",

year = "2025",

doi = "10.3233/FAIA250669",

language = "English",

volume = "408",

pages = "486--488",

journal = "Frontiers in Artificial Intelligence and Applications",

issn = "0922-6389",

publisher = "IOS Press",

}

TY - JOUR

T1 - Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making

AU - Aydin, Hüseyin

AU - Godin-Dubois, Kevin

AU - Goncalvez Braz, Libio

AU - Den Hengst, Floris

AU - Baraka, Kim

AU - Çelikok, Mustafa Mert

AU - Sauter, Andreas

AU - Wang, Shihan

AU - Oliehoek, Frans A.

PY - 2025

Y1 - 2025

N2 - We present SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments), a generic framework to support experiments with RL agents and humans. It consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, and deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide variety of research questions related to the interaction between humans and RL agents and aims to standardize the field of study on RL in human contexts.

AB - We present SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments), a generic framework to support experiments with RL agents and humans. It consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, and deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide variety of research questions related to the interaction between humans and RL agents and aims to standardize the field of study on RL in human contexts.

KW - experimentation

KW - hybrid AI

KW - reinforcement learning

KW - software

UR - http://www.scopus.com/inward/record.url?scp=105020962880&partnerID=8YFLogxK

U2 - 10.3233/FAIA250669

DO - 10.3233/FAIA250669

M3 - Article

AN - SCOPUS:105020962880

SN - 0922-6389

VL - 408

SP - 486

EP - 488

JO - Frontiers in Artificial Intelligence and Applications

JF - Frontiers in Artificial Intelligence and Applications

ER -

Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this