בניין מדעי המחשב

ALON COHEN

GOOGLE RESEARCH – TEL-AVIV

ירצה על

Will lecture on

Between Online Learning and Reinforcement Learning

In this talk I will describe some of my work around Online Learning and Reinforcement Learning. 

Online Learning is a classic sub-domain of Machine Learning that has provided endless contributions to fields such as Statistical Learning, Optimization, Decision Making and others. 

Unlike Reinforcement Learning which focuses on planning long-term decisions in the face of a non-adversarial environment, Online Learning focuses on making short-term decisions in the face of an adversary - and doing so efficiently. 

In my research, therefore, I am interested in the potential interface between these fields, looking to design efficient algorithms for long-term decision making in the face of a possibly adversarial environment---a problem with many real-life use cases. 

I will focus on two works that leverage efficient Online Learning algorithms for learning Linear Quadratic Regulators and Stochastic Shortest Path problems.

Zoom link:  

https://us02web.zoom.us/j/83383478356