Ismael T. Freire

This paper introduces the Epistemic Replay Algorithm (ERA) to explain hippocampal replay by integrating curiosity and reward, showing it better accounts for replay properties than non-curious models.

This paper introduces a biomimetic agent that autonomously regulates internal needs through a neural mass model, outperforming control agents in efficiency and stability.

This paper introduces MoHA, a model that integrates motivational and visual inputs to generate cognitive maps, enabling adaptive navigation in reinforcement learning agents.