AI Seminar Series 2022: Bo Dai

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 September 9, Bo Dai — a researcher with Google's Brain Team — presented "Representation-based Reinforcement Learning" at the AI Seminar.

The majority reinforcement learning (RL) algorithms are largely categorized as model-free and model-based based on whether a simulation model is used in the algorithm. However, both of these two categories have their issues, especially incorporating with function approximation: the exploration with arbitrary function approximation in model-free RL algorithms is difficult; while optimal planning becomes intractable in model-based RL algorithms with neural simulators.

In this talk, Dai presents recent work on exploiting the power of representation in RL to bypass these difficulties. His team designed practical algorithms for extracting useful representations, with the goal of improving statistical and computational efficiency in exploration vs. exploitation tradeoff and empirical performance in RL. Dai provides a rigorous theoretical analysis of the algorithm and demonstrates its practical superior performance over the existing state-of-the-art empirical algorithms on several benchmarks.

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.