Amii at ICML 2021: Accepted papers & workshops

The work of Amii researchers is being featured at the 38th annual International Conference on Machine Learning (ICML), running online this year from July 18 to 24.

ICML is the premier gathering of professionals dedicated to the advancement of the branch of AI known as machine learning (ML). Globally renowned for presenting and publishing cutting-edge research on all aspects of ML and application areas, the conference is within the top ten highest-ranked ML & AI conferences in the world based on h-index and Impact Score values (see: Google Scholar and Guide2Research).

Amii Fellows and Canada CIFAR AI Chairs – professors at the University of Alberta, University of British Columbia and Carleton University – as well as other Amii researchers have 23 papers included in the proceedings:

Accepted Papers

* indicates Amii researcher or alum

A Distribution-dependent Analysis of Meta Learning

• Mikhail Konobeev*, Ilja Kuzborskij, Csaba Szepesvári*

Average-Reward Off-Policy Policy Evaluation with Function Approximation

• Shangtong Zhang, Yi Wan*, Richard Sutton*, Shimon Whiteson

Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization

• Wesley Chung, Valentin Thomas, Marlos C. Machado*, Nicolas Le Roux

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

• Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári*, Mengdi Wang

Characterizing the Gap Between Actor-Critic and Policy Gradient

• Junfeng Wen*, Saurabh Kumar, Ramki Gummadi, Dale Schuurmans*

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games

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

Emphatic Algorithms for Deep Reinforcement Learning

• Ray Jiang, Tom Zahavy, Zhongwen Xu, Adam White*, Matteo Hessel, Charles Blundell, Hado van Hasselt

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

• Julien Perolat, Remi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro Ortega, Neil Burch*, Thomas Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot*, Karl Tuyls

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

• Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvári*

Learning and Planning in Average-Reward Markov Decision Processes

• Yi Wan*, Abhishek Naik*, Richard Sutton*

LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs

• Hongyu Ren, Hanjun Dai, Bo Dai, Xinyun Chen, Michihiro Yasunaga, Haitian Sun, Dale Schuurmans*, Jure Leskovec, Denny Zhou

Leveraging Non-uniformity in First-order Non-convex Optimization

• Jincheng Mei*, Yue Gao*, Bo Dai, Csaba Szepesvári*, Dale Schuurmans*

Meta-Thompson Sampling

• Branislav Kveton, Mikhail Konobeev*, Manzil Zaheer, Chih-wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvári*

On the Optimality of Batch Policy Optimization Algorithms

• Chenjun Xiao*, Yifan Wu*, Jincheng Mei*, Bo Dai, Tor Lattimore*, Lihong Li*, Csaba Szepesvári*, Dale Schuurmans*

Parameterless Transductive Feature Re-representation for Few-Shot Learning

• Wentao Cui, Yuhong Guo*

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

• Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno*, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Gu

Randomized Exploration in Reinforcement Learning with General Value Function Approximation

• Haque Ishfaq, Qiwen Cui, Viet Nguyen, Alex Ayoub*, Zhuoran Yang, Zhaoran Wang, Doina Precup, Lin Yang

Revisiting Peng's Q(λ) for Modern Reinforcement Learning

• Tadashi Kozuno*, Yunhao Tang, Mark Rowland, Remi Munos, Steven Kapturowski, Will Dabney, Michal Valko, David Abel

RNNRepair: Automatic RNN Repair via Model-based Analysis

• Xiaofei Xie, Wenbo Guo, Lei Ma*, Wei Le, Jian Wang, Lingjun Zhou, Yang Liu, Xinyu Xing

Robust Asymmetric Learning in POMDPs

• Andrew Warrington, Jonathan Lavington*, Adam Ścibior, Mark Schmidt*, Frank Wood

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

• Botao Hao, Yaqi Duan, Tor Lattimore*, Csaba Szepesvári*, Mengdi Wang

Tractable structured natural-gradient descent using local parameterizations

• Wu Lin*, Frank Nielsen, Khan Emtiyaz, Mark Schmidt*

Valid Causal Inference with (Some) Invalid Instruments

• Jason Hartford*, Victor Veitch, Dhanya Sridhar, Kevin Leyton-Brown*

Workshops

Reinforcement Learning for Real Life

• Co-organized by Yuxi Li, Minmin Chen, Omer Gottesman, Lihong Li, Zongqing Lu, Rupam Mahmood*, Niranjani Prasad, Zhiwei (Tony) Qin, Csaba Szepesvári*, Matthew Taylor*

Workshop on Reinforcement Learning Theory

• Co-organized by Shipra Agrawal, Simon Du, Niao He, Csaba Szepesvári*, Lin Yang

Other Activities

Trivia Night hosted by Amii

• Date: Friday, July 23 (3 - 4:30 pm MST)
• Description: Join us for a virtual trivia night and an opportunity to learn more about the work we are doing at Amii! Teams will be assembled during the event and the winning team will walk away with a $25 gift card towards a celebratory meal from UberEATS.

Mentoring Program

• Date: July 19-23
• Description: Researchers from around the world are welcome to join these special sessions with leading AI & ML researchers. Mentors will share their research, career and life advice, and answer questions. Check out the list of amazing mentors here, including our own Marlos C. Machado, Nidhi Hegde, Matthew E. Taylor, Michael Bowling, Adam White and Robert Holte!

Service

In addition to his work being featured at the ICML Conference, Adam White also served as Social Chair.

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