Doina Precup

Doina Precup teaches at McGill while conducting fundamental research on reinforcement learning, working in particular on AI applications in areas that have a social impact, such as health care. She’s interested in machine decision-making in situations where uncertainty is high.

She is a senior fellow of the Canadian Institute for Advanced Research, fellow of the Association for the Advancement of Artificial Intelligence and she also heads the Montreal office of Deepmind.

Specialist In: Artificial intelligence, machine learning, reinforcement learning, reasoning and planning under uncertainty, applications.

Publications

Options of Interest: Temporal Abstraction with Interest Functions

Neural Transfer Learning for Cry-based Diagnosis of Perinatal Asphyxia

Variational State Encoding as Intrinsic Motivation in Reinforcement Learning

Per-Decision Option Discounting

Off-Policy Deep Reinforcement Learning without Exploration