Amii is proud to share the work of our researchers at the 20th annual International Conference on Autonomous Agents and Multiagent Systems (AAMAS). The conference takes place online from May 3 to 7, 2021.

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology, as well as providing an internationally renowned, high-profile forum for publishing and finding out about the latest developments in the field.

Accepted papers largely focus on reinforcement learning, a branch of machine learning that enables AI systems to learn through experience; Amii researchers are pioneers and leaders in this area.

Amii Fellows and Canada CIFAR AI Chairs – professors at the University of Alberta – are included in the proceedings, as well as other Amii researchers (* indicates Amii researcher or alum):

Accepted Papers

Main Track: Full Papers

Partially Observable Mean Field Reinforcement Learning

• Sriram Ganapathi Subramanian, Matthew E. Taylor, Mark Crowley and Pascal Poupart

Main Track: Extended Abstracts

Sound Algorithms in Imperfect Information Games

• Michal Sustr, Martin Schmid*, Matej Moravčík*, Neil Burch*, Marc Lanctot* and Michael Bowling

Blue Sky Ideas Track

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems

• Yaodong Yang, Matthew E. Taylor, Jun Luo, Ying Wen, Oliver Slumbers, Daniel Graves, Haitham Bou Ammar and Jun Wang

Workshop Papers

The following papers are being featured at the Adaptive & Learning Agents (ALA) workshop:

The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning

• Vlad Tkachuk*, Sriram Ganapathi, and Matthew E. Taylor

Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging

• Nikunj Gupta, Gopalakrishnan Srinivasaraghavan, Swarup Mohalik, Nishant Kumar and Matthew E. Taylor

Work-in-progress: Comparing Feedback Distributions in Limited Teacher-Student Settings

• Calarina Muslimani*, Kerrick Johnstonbaugh and Matthew Taylor

Service

In addition to his work being featured at the AAMAS Conference, Matthew E. Taylor also served on the Senior Programme Committee.

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