Affectively Framework: Towards Human-like Affect-Based Agents
Published in IEEE International Conference on Affective Computing and Intelligent Interaction Workshops (ACIIW), 2024
Recommended citation: Barthet, M., Khalifa, A., Liapis, A., & Yannakakis, G. N. (2024). Affectively Framework: Towards Human-like Affect-Based Agents. In Proceedings of the 12th IEEE International Conference on Affective Computing and Intelligent Interaction Workshops (ACIIW).
Game environments offer a unique opportunity for training virtual agents due to their interactive nature, which provides diverse play traces and affect labels. Despite their potential, no reinforcement learning framework incorporates human affect models as part of their observation space or reward mechanism. To address this, we present the \emph{Affectively Framework}, a set of Open-AI Gym environments that integrate affect as part of the observation space. This paper introduces the framework and its three game environments and provides baseline experiments to validate its effectiveness and potential.