TECHNICAL WORKSHOP SERIES - Foundations of Q-learning (2nd Offering) By: Xiaofeng (Michael) Liu

Thursday, June 6, 2024 - 12:30

Technical Workshop Series

Foundations of Q-learning (2nd Offering)

Presenter:  Xiaofeng (Michael) Liu

Date: Thursday, June 6th, 2024

Time:  12:30 PM

Location: 4th Floor (Workshop space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)

 

Abstract: 

Reinforcement learning (RL) is training machine learning models to make a sequence of decisions. Q-learning is a type of RL with a model-free environment that achieves learning by interaction with the environment instead of transition probabilities. This workshop will introduce the principle of Q-learning.

 

Workshop Outline:

•             What Q-learning is

•             Characteristics of Q-learning models

•             What Q-values are

•             What temporal differences are

•             What the Bellman Equation is

•             How the Q-learning process works

•             Practice

 

Prerequisites:

Principle of RL

 

Biography: 

Michael is a PhD Candidate in Computer Science. His main research interests are mainly focused on Congestion Control for V2V communication in VANET (Vehicular Ad hoc Network).

 

MAC STUDENTS ONLY - Register here