AI Seminar Series 2020: Marlos C. Machado, An operator view of policy gradient methods

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On November 27, 2020, research scientist at Google Brain (Montreal) and Amii alumnus Marlos C. Machado presented “An operator view of policy gradient methods”.

Policy gradient methods can be seen as iteratively applying two operators: an improvement operator and a projection operator. Marlos explains that the improvement operator perspective enables us to better understand connections between value-based methods and policy gradient methods.

Watch the full presentation below:

Keep up-to-date on the AI Seminar Series by signing up for the mailing list.

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.