Subgoal search
Planning and search have been immensely studied topics in AI research. However, many questions still stay unanswered. In my talk, I will explore topics on the intersection of planning and learning. A general question is how learning methods can be used to make planning more efficient or, conversely, how planning can mitigate errors in learned models.
Bio
Piotr Miłoś is a professor at the Polish Academy of Sciences and a visiting professor at the University of Oxford. He specialises in machine learning and leads a research group focusing on reinforcement learning. Prof Milos has a strong mathematical background in probability theory. He actively works towards developing machine learning research in Poland. This includes hosting a reinforcement learning seminar and co-organize reinforcement learning course (first in Poland), and being a scientific advisor of the ML in PL association.