Advanced Reinforcement Learning & Data Science for Social Impact with Vukosi Marivate

800 800 The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

In this, the final show of our Deep Learning Indaba series, we speak with Vukosi Marivate, Chair of Data Science at the University of Pretoria and a co-organizer of the Indaba.

My conversation with Vukosi fell into two distinct parts. The first part focused on his PhD research in the area of reinforcement learning, discussing several advanced RL scenarios including inverse RL, multiple agent RL, and using RL when we have incomplete knowledge of the environment. We then moved on to discuss his current research, which broadly falls under the banner of data science with social impact. Specifically, we review several of the applications he and his students are currently exploring in areas such as public safety and energy.

Thanks to our Sponsor!

If you’ve got an interest in machine learning research and want to level-up your skills in one of the top ML research groups in the world, you should take a moment to learn more about the Google AI Residency program, which recently opened up applications for prospective 2019 Residents! The Google AI Residency is a one-year machine learning research training program with the goal of helping individuals from all over the world and with a diverse set of educational and professional backgrounds become successful machine learning researchers. Find out more about the program at

About Vukosi

Mentioned in the Interview

“More On That Later” by Lee Rosevere licensed under CC By 4.0

Leave a Reply

Your email address will not be published.