Please note that this meetup will be an online event. Please use this link to access the event on March 26th. https://virtual.skills.network/b/jos-mu3-j67

In preparation for the event if you would like to gain some insight, here is a link to the optional reading… Reinforcement Learning: An Introduction:http://incompleteideas.net/book/the-book-2nd.html

To better accommodate our participants, please register at https://cocl.us/meetupmarlab

This is the second in a series of meetups on Deep learning.

In this meetup, we will provide an overview of some fundamental methods of Reinforcement Learning; these methods are the bases for more complex methods you see solving some of the world’s most exciting problems. We will first review the Multi-armed Bandit problem. This will be a backdrop for learning Finite Markov Decision Processes and Dynamic Programming methods like Iterative Policy Evaluation and Policy Iteration. Don’t forget to bring your laptops as this meetup will have labs that will be hands on.

Please note that the labs in the session will be done using our labs platform. To access our platform, please register at https://labs.cognitiveclass.ai.

Audience: Beginners in Data Science and Data Science Enthusiasts

Presenters: Joseph Santarcangelo, Data Scientist at IBM (https://www.linkedin.com/in/joseph-santarcangelo-50398b136/).