"revisiting the arcade learning environment: evaluation protocols and open problems for general agents"
The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community, leading to some high-profile success stories such as the much publicized Deep Q-Networks (DQN). In this talk I will take a big picture look at how the ALE is being used by the research community. I will summarize some of the lessons learned by the community, highlighting some subtle issues that are often overlooked. I then use this discussion to suggest some methodological best practices and to briefly discuss new benchmark results using these best practices. In the final part of the talk I'll revisit the challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.
Bio: Marlos C. Machado is a Ph.D. candidate working under the supervision of Michael Bowling and Marc G. Bellemare at the University of Alberta. His research interests lie broadly in Artificial Intelligence and particularly focus on Machine Learning/Reinforcement Learning. His recent work investigates how temporally extended actions, learned from experience, can be used to assist agents to better explore the environment they are in. He is also particularly interested in the Arcade Learning Environment as an evaluation platform for generally competent agents.
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.