Affectively Framework: Towards Human-Like Affect-Based Agents

• Published in: 2024 12th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) pp. 144 - 148
• Main Authors: Barthet, Matthew, Gallotta, Roberto, Khalifa, Ahmed, Liapis, Antonios, Yannakakis, Georgios N.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15.09.2024
• Subjects: Affective computing; baselines; Conferences; Games; Reinforcement learning; Software packages; Training; Virtual environments

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 m...