A reinforcement-learning meta-control architecture based on the dual-process theory of moral decision-making

Maier, M., Cheung, V., and Lieder, F. (2023). A Reinforcement-Learning Meta-Control Architecture Based on the Dual-Process Theory of Moral Decision-Making. [Accepted at the 37th Conference on Neural Information Processing Systems (NeurIPS 2023) WorkshopAI Meets Moral Philosophy and Moral Psychology]. https://osf.io/j6fhk_v1