Towards an Experimentation Platform for Hybrid Human-AI Sequential Decision-Making
Hüseyin Aydin (Universiteit Utrecht)
Kevin Godin-Dubois (Vrije Universiteit Amsterdam)
Libio Goncalvez Braz (Universiteit Utrecht)
Floris Den Hengst (Vrije Universiteit Amsterdam)
Kim Baraka (Vrije Universiteit Amsterdam)
Mustafa Mert Çelikok (TU Delft - Sequential Decision Making)
Andreas Sauter (Vrije Universiteit Amsterdam)
Shihan Wang (Universiteit Utrecht)
Frans A. Oliehoek (TU Delft - Sequential Decision Making)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
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.
help_outline