Amii papers published & researcher contributions at AAAI 2021

Amii is proud to share the work of our researchers being featured at the 35th AAAI Conference on Artificial Intelligence, running online this year from February 2 to 9.

The AAAI Conference promotes research in artificial intelligence (AI) and fosters scientific exchange between researchers, practitioners, scientists, students and engineers in AI and its affiliated disciplines. Based on h-index and Impact Score values, AAAI is within the top five highest-ranked ML & AI conferences in the world (see: Google Scholar and Guide2Research). According to the Program Co-chair Kevin Leyton-Brown (Canada CIFAR AI Chair at Amii and Professor at the University of British Columbia), a record 9,034 papers were submitted this year -- of these, 7,911 were reviewed and 1,692 (21%) accepted.

Accepted papers from Amii researchers cover a range of topics, including the introduction of CAPI, a novel algorithm that combines common knowledge among a team of agents as a way of discovering optimal joint policies, as well as EfficientDeRain, which is able to process a rainy image within 10~ms over 80 times faster than the state-of-the-art method, while achieving similar de-rain effects.

In addition, Amii Fellow and Canada CIFAR AI Chair Michael Bowling will be honoured as a new AAAI Fellow at AAAI 2021.

Amii Fellows and Canada CIFAR AI Chairs – professors at the University of Alberta and University of Regina – are included in the proceedings, as well as other Amii researchers:

Accepted Papers (Main Track)

Decision-Guided Weighted Automata Extraction from Recurrent Neural Networks

• Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun

Deep Probabilistic Canonical Correlation Analysis

• Mahdi Karami, Dale Schuurmans

EfficientDeRain: Learning Pixel-Wise Dilation Filtering for High-Efficiency Single-Image Deraining

• Qing Guo, Jingyang Sun, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Wei Feng, Yang Liu, Jianjun Zhao

Hindsight and Sequential Rationality of Correlated Play

• Dustin Morrill, Ryan D'Orazio, Reca Sarfati, Marc Lanctot, James R Wright, Amy R Greenwald, Michael Bowling

Improving the Performance-Compatibility Tradeoff with Personalized Objective Functions

• Jonathan Martinez, Kobi Gal, Ece Kamar, Levi H. S. Lelis

Necessary and Sufficient Conditions for Avoiding Reopenings in Best First Suboptimal Search with General Bounding Functions

• Jingwei Chen, Nathan R Sturtevant

Policy-Guided Heuristic Search with Guarantees

• Laurent Orseau, Levi H. S. Lelis

Precision-Based Boosting

• Mohammad Hossein Nikravan, Marjan Movahedan, Sandra Zilles

Programmatic Strategies for Real-Time Strategy Games

• Julian Mariño, Rubens Moraes, Tassiana Oliveira, Claudio Toledo, Levi H. S. Lelis

Solving Common-Payoff Games with Approximate Policy Iteration

• Samuel Sokota, Edward Lockhart, Finbarr Timbers, Elnaz Davoodi, Ryan D'Orazio, Neil Burch, Martin Schmid, Michael Bowling, Marc Lanctot

TAC: Towered Actor Critic for Handling Multiple Action Types in Reinforcement Learning for Drug Discovery

• Sai Krishna Gottipati, Yashaswi Pathak, Boris Sattarov, Sahir, Rohan Nuttall, Mohammad Amini, Matthew E. Taylor, Sarath Chandar

Workshop Paper Publication

Measuring the Solution Strength of Learning Agents in Adversarial Perfect Information Games featured at the Reinforcement Learning in Games Workshop

• Zaheen Farraz Ahmad, Nathan Sturtevant, Michael Bowling

Service

Amii researchers have also served in the organization of the conference:

Program Co-chair

• Kevin Leyton-Brown

Senior Member Track Co-Chair

• Nathan Sturtevant

Job Fair Co-Chair

• Matthew E. Taylor

Area Chairs

• Csaba Szepesvari
• Matthew Taylor

Senior Program Committee

• Levi Lelis
• Nathan Sturtevant
• Osmar Zaiane

Program Committee

• Li Cheng
• Md Solimul Chowdhury
• Srijita Das
• Trevor Davis
• Kristopher De Asis
• Johannes Guenther
• Matthew Guzdial
• Nidhi Hegde
• J. Hernandez-Garcia
• Ajin Joseph
• Abou-Moustafa Karim
• Chenglin Li
• Jincheng Mei
• Lili Mou
• Abhishek Naik
• Di Niu
• Matthew Schlegel
• Ting Han Wei
• Junfeng Wen
• James Wright
• Chenjun Xiao
• Kenny Young
• Muhammad Yousefnezhad
• Mingjun Zhao

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