BYU

Abstract by Spencer Reschke

Personal Infomation


Presenter's Name

Spencer Reschke

Degree Level

Undergraduate

Abstract Infomation


Department

Mathematics

Faculty Advisor

Mark Hughes

Title

Deep Reinforcement Learning and Constructive Proofs in Topology

Abstract

Low-dimensional topology has numerous examples of problems whose solutions require constructing sequences of operations taken from a fixed set of moves. In knot theory, constructing genus-minimizing slice surfaces of a knot is an example of such a problem. In this talk we’ll discuss how recent advances in deep reinforcement learning can be leveraged to construct these surfaces. In particular we’ll discuss deep Q-learning and its modern improvements such as double Q-learning, dueling architextures, prioritized experience replay, and asynchronous methods.