Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.19245 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916594720964608 |
|---|---|
| author | Aydın, Hüseyin Godin-Dubois, Kevin Braz, Libio Goncalvez Hengst, Floris den Baraka, Kim Çelikok, Mustafa Mert Sauter, Andreas Wang, Shihan Oliehoek, Frans A. |
| author_facet | Aydın, Hüseyin Godin-Dubois, Kevin Braz, Libio Goncalvez Hengst, Floris den Baraka, Kim Çelikok, Mustafa Mert Sauter, Andreas Wang, Shihan Oliehoek, Frans A. |
| contents | Reinforcement learning (RL) offers a general approach for modeling and training AI agents, including human-AI interaction scenarios. In this paper, we propose SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments) to address the need for a generic framework to support experiments with RL agents and humans. Its modular design consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, 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, including those related to interactive reward specification and learning, learning from human feedback, action delegation, preference elicitation, user-modeling, and human-AI teaming. The platform is based on a generic interface for human-RL interactions that aims to standardize the field of study on RL in human contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19245 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments Aydın, Hüseyin Godin-Dubois, Kevin Braz, Libio Goncalvez Hengst, Floris den Baraka, Kim Çelikok, Mustafa Mert Sauter, Andreas Wang, Shihan Oliehoek, Frans A. Artificial Intelligence Human-Computer Interaction Reinforcement learning (RL) offers a general approach for modeling and training AI agents, including human-AI interaction scenarios. In this paper, we propose SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments) to address the need for a generic framework to support experiments with RL agents and humans. Its modular design consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, 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, including those related to interactive reward specification and learning, learning from human feedback, action delegation, preference elicitation, user-modeling, and human-AI teaming. The platform is based on a generic interface for human-RL interactions that aims to standardize the field of study on RL in human contexts. |
| title | SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2501.19245 |