SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments
It provides a standardized tool for researchers in human-AI interaction, though it is incremental as it builds on existing RL and interface concepts.
The paper tackles the lack of a generic framework for experiments involving reinforcement learning agents and humans by proposing SHARPIE, a modular platform that includes environment wrappers, a web interface, and logging utilities, enabling researchers to study various human-AI interaction questions.
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.