Back to All Events

ai seminar - marlos machado

  • University of Alberta 3-33 Computing Sciences Centre Edmonton AB Canada (map)

"a laplacian framework for option discovery in reinforcement learning"

Part of the Alberta Machine Intelligence Institute, Marlos C. Machado is a 4th year Ph.D. student in the University of Alberta's Department of Computing Science, supervised by Amii's Michael Bowling.
Marlos' research interests lie broadly in artificial intelligence with a particular focus on machine learning and reinforcement learning. Marlos is also a member of the Reinforcement Learning & Artificial Intelligence research group, led by Amii's Richard S. Sutton.

Abstract: Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-RL is a well known approach for representation learning in MDPs. The representations learned with this framework are called proto-value functions (PVFs). In this paper we address the option discovery problem by showing how PVFs implicitly define options. We do it by introducing \emph{eigenpurposes}, intrinsic reward functions derived from the learned representations. The options discovered from eigenpurposes traverse the principal directions of the state space. They are useful for multiple tasks because they are independent of the agents' intentions. Moreover, by capturing the diffusion process of a random walk, different options act at different time scales, making them helpful for exploration strategies. We demonstrate features of eigenpurposes in traditional tabular domains as well as in Atari 2600 games.


ai seminar series

Fridays at noon, Amii and the Department of Computing Science host AI Seminars, engaging presentations on topics in the broad field of artificial intelligence. With speakers from the University of Alberta and other world-leading groups, the talks give AI enthusiasts a friendly way of engaging with the latest trends and topics in research and development.

Seminars are open to the public, and no registration is required, though seating is limited and on a first-come-first-served basis. Topics range from foundational theoretical work to innovative applications of artificial intelligence technologies.

If you would like to present at an upcoming AI Seminar, please contact Colin Bellinger.

Join the AI Seminar mailing list to stay up-to-date on all the latest presentations

    Earlier Event: May 12
    ai seminar - russ greiner
    Later Event: May 31
    the tea time talks: rich sutton