AI Seminar Series 2022: Matthew Schlegel

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 Nov. 25, Matthew Schlegel, a Ph. D. student at the Unversity of Alberta – presented " Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning" at the AI Seminar.

Abstract:

Building and maintaining state to learn policies and value functions is critical for deploying reinforcement learning (RL) agents in the real world. Recurrent neural networks (RNNs) have become a key point of interest for the state-building problem, and several large-scale reinforcement learning agents incorporate recurrent networks. While RNNs have become a mainstay in many RL applications, many choices are often under-reported and contain critical implementation details to improve performance. In his talk, we discuss one axis on which RNN architectures can be (and have been) modified for use in RL. Specifically, Schlegel investigates how action information incorporates into the state update function of a recurrent cell.

While action as the focus presents as an intuitive choice, several lines of research in cognitive science highlight the importance of action in perception. Schlegel discusses several architectural choices centered on action and empirically evaluate the resulting architectures on a set of illustrative domains. This empirical evaluation includes an analysis of the learned state in a prediction problem, behavioral experiments, and performance when observations take the form of images and agent-centric sensor readings.

Finally, he discusses future work in developing and analyzing recurrent cells and key challenges needing attention in the partially observable setting.

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.