Dustin Morrill

Artificial intelligence researcher

​

Currently

Senior research scientist at Sony AI working on AI to play Sony games and support game development. For example, GT Sophy and the Coachable Agents research paper. I use algorithmic game theory and reinforcement learning to design robust and performant AI systems in challenging domains.

Education

2016-2022 Ph.D., Computing Science, University of Alberta

Co-advisors: Professor Michael Bowling and Professor Amy Greenwald

Thesis Title: Hindsight Rational Learning for Sequential Decision-Making: Foundations and Experimental Applications

2014-2016 M.Sc., Computing Science, University of Alberta

Advisor: Professor Michael Bowling

Thesis Title: Using Regret Estimation to Solve Games Compactly

2008-2013 B.Sc., With Honors in Computing Science, University of Alberta

Distinctions: First Class Honors, Industrial Internship Program

Publications

Theses

2022 Dustin Morrill. Hindsight Rational Learning for Sequential Decision-Making: Foundations and Experimental Applications. Ph.D. thesis, Department of Computing Science, University of Alberta, Sep 1, 2022. Edmonton, Canada.

2016 Dustin Morrill. Using Regret Estimation to Solve Games Compactly. M.Sc. thesis, Department of Computing Science, University of Alberta, Apr 1, 2016. Edmonton, Canada.

Journal Articles

2025 Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, and Michael Bowling. Learning to Be Cautious. In Transactions on Machine Learning Research, Oct 1, 2025.

2017 Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, and Michael Bowling. DeepStack: Expert-Level Artificial Intelligence in Heads-Up No-Limit Poker. In Science, Mar 2, 2017.

Refereed Conferences

2023 Dustin Morrill, Thomas J. Walsh, Daniel Hernandez, Peter R. Wurman, and Peter Stone. Composing Efficient, Robust Tests for Policy Selection. At the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI 2023), Jul 31, 2023. Pittsburgh, USA. [Acceptance Rate: 31.2%].

2021 Dustin Morrill, Ryan D’Orazio, Marc Lanctot, James R. Wright, Michael Bowling, and Amy Greenwald. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. At the Thirty-Eighth International Conference on Machine Learning (ICML 2021), Jul 18, 2021. Virtual. [Acceptance Rate: 21.5%].

2021 Dustin Morrill, Ryan D’Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, and Michael Bowling. Hindsight and Sequential Rationality of Correlated Play. At the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), Feb 2, 2021. Virtual. [Acceptance Rate: 21.4%].

2020 Daniel Hennes[1], Dustin Morrill[1], Shayegan Omidshafiei[1], Remi Munos, Julien Perolat, Marc Lanctot, Audrunas Gruslys, Jean-Baptiste Lespiau, Paavo Parmas, Edgar Duéñez-Guzmán, and Karl Tuyls. Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients. At the Nineteenth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2020), May 9, 2020. Auckland, New Zealand. [Acceptance Rate: 23.0%].

2020 Ryan D’Orazio[1], Dustin Morrill[1], James R. Wright, and Michael Bowling. Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization. At the Nineteenth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2020), May 9, 2020. Auckland, New Zealand. [Acceptance Rate: 23.0%].

2019 Edward Lockhart, Marc Lanctot, Julien Pérolat, Jean-Baptiste Lespiau, Dustin Morrill, Finbarr Timbers, and Karl Tuyls. Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descent. At the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019), Aug 10, 2019. Macao, China. [Acceptance Rate: 17.9%].

2018 Neil Burch, Martin Schmid, Matej Moravčík, Dustin Morrill, and Michael Bowling. AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Games. At the Thirty-Second AAAI Conference on Artificial Intelligence, Feb 2, 2018. New Orleans, USA. [Acceptance Rate: 24.6%].

2015 Kevin Waugh, Dustin Morrill, J. Andrew Bagnell, and Michael Bowling. Solving Games with Functional Regret Estimation. At the Twenty-Ninth AAAI Conference on Artificial Intelligence, Jan 25, 2015. Austin, USA. Pages 2138–2145. [Acceptance Rate: 26.7%].

Workshop Articles

2022 Dustin Morrill, Amy Greenwald, and Michael Bowling. The Partially Observable History Process. AAAI-22 Workshop on Reinforcement Learning in Games, Feb 28, 2022. Vancouver, Canada.

2019 Ryan D’Orazio, Dustin Morrill, and James R. Wright. Bounds for Approximate Regret-Matching Algorithms. Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning (SGO&ML) at NeurIPS 2019, Dec 14, 2019. Vancouver, Canada.

Technical Reports

2026 Roberto Capobianco, Harm van Seijen, Nolan D. Bard, Neil Burch, Fatima Davelouis, Josh Davidson, Alisa Devlic, Yunshu Du, Ishan Durugkar, Siddhant Gangapurwala, Daniel Hernandez, G. Zacharias Holland, Sahil Jain, Kenta Kawamoto, Raksha Kumaraswamy, Patrick MacAlpine, Dustin Morrill, Declan Oller, Francesco Riccio, Akanksha Saran, Craig Sherstan, Kaushik Subramanian, Thomas J. Walsh, Samuel Barrett, Kizza N. Frisbee, Mady Govil, Johannes Günther, Varun R. Kompella, James A. MacGlashan, Maxwell Svetlik, Michael D. Thomure, Jaden B. Travnik, Kevin Waugh, Elahe Aghapour, Florian Fuchs, Andreanne Lemay, Shruti Mishra, Takuma Seno, Peter Stone, Michael Spranger, and Peter R. Wurman. Coachable Agents for Interactive Gameplay. arXiv, Jul 1, 2026.

2021 Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, and Michael Bowling. Learning to Be Cautious. arXiv, Oct 29, 2021.

2020 Audrūnas Gruslys, Marc Lanctot, Rémi Munos, Finbarr Timbers, Martin Schmid, Julien Perolat, Dustin Morrill, Vinicius Zambaldi, Jean-Baptiste Lespiau, John Schultz, Mohammad Gheshlaghi Azar, Michael Bowling, and Karl Tuyls. The Advantage Regret-Matching Actor-Critic. arXiv, Aug 27, 2020.

2019 Marc Lanctot, Edward Lockhart, Jean-Baptiste Lespiau, Vinicius Zambaldi, Satyaki Upadhyay, Julien Pérolat, Sriram Srinivasan, Finbarr Timbers, Karl Tuyls, Shayegan Omidshafiei, Daniel Hennes, Dustin Morrill, Paul Muller, Timo Ewalds, Ryan Faulkner, János Kramár, Bart De Vylder, Brennan Saeta, James Bradbury, David Ding, Sebastian Borgeaud, Matthew Lai, Julian Schrittwieser, Thomas Anthony, Edward Hughes, Ivo Danihelka, and Jonah Ryan-Davis. OpenSpiel: A Framework for Reinforcement Learning in Games. arXiv, Aug 26, 2019.

Work Experience

2022-present Sony AI, Edmonton

Senior Research Scientist

2019-2022 University of Alberta, Edmonton

Graduate Research Assistant

Mar-Aug 2019 DeepMind, Edmonton

Research Scientist Intern

2014-2019 University of Alberta, Edmonton

Graduate Research Assistant

May-Dec 2018 University of Alberta, Edmonton

Undergraduate Research Mentor

Jan-Apr 2018 Hyperborean Inc., Edmonton

Application Developer

May-Aug 2013 University of Alberta, Edmonton

Undergraduate Researcher

2011-2013 University of Alberta, Edmonton

Part-Time Undergraduate Researcher

May-Aug 2010 University of Alberta, Edmonton

Undergraduate Researcher

May-Aug 2009 University of Alberta, Edmonton

Undergraduate Researcher

Supervision

2026-present Diego Gomez at Sony AI

M.Sc., Universidad de Los Andes, Colombia

Jan-Aug 2023 Prabhat Nagarajan at Sony AI

M.Sc., University of Texas at Austin

2020-2021 Montaser Mohammedalamen at University of Alberta

M.Sc., African Institute for Mathematical Sciences

2020-2021 Alexander Sieusahai at University of Alberta

B.Sc., University of Alberta

2018-2019 Fatima Davelouis Gallardo at University of Alberta

B.Sc., University of Alberta

Presentations and Outreach

Seminars

Sep 2021 Dustin Morrill, Ryan D’Orazio, Marc Lanctot, James R. Wright, Michael Bowling, and Amy Greenwald. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. At DeepMind Multi-Agent Weekly Meeting.

Aug 2021 Dustin Morrill, Ryan D’Orazio, Marc Lanctot, James R. Wright, Michael Bowling, and Amy Greenwald. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. At Berkeley Multi-Agent Reinforcement Learning Reading Group.

Jul 2021 Dustin Morrill, Ryan D’Orazio, Marc Lanctot, James R. Wright, Michael Bowling, and Amy Greenwald. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. At Alberta Machine Intelligence Institute AI Seminar.

Jun 2021 Dustin Morrill. Extensive-Form Regret Minimization: A Scalable Unifying Framework for Hindsight Rational Learning. At Brown Robotics Group Meeting.

Apr 2021 Dustin Morrill, Ryan D’Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, and Michael Bowling. Hindsight Rationality and Deviation Types in EFGs. At Berkeley Multi-Agent Reinforcement Learning Reading Group.

Mar 2021 Dustin Morrill, Ryan D’Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, and Michael Bowling. Hindsight Rationality and Deviation Types in EFGs. At Alberta Machine Intelligence Institute AI Seminar.

Mar 2021 Dustin Morrill, Ryan D’Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, and Michael Bowling. Hindsight Rationality and Deviation Types in EFGs. At DeepMind Game Theory Group.

Apr 2020 Dustin Morrill. Thesis Proposal. At University of Alberta.

Oct 2019 Dustin Morrill. Internship Work Follow-Up Presentation. At DeepMind Alberta.

Aug 2019 Dustin Morrill. Internship Conclusion Presentation. At DeepMind Alberta.

Aug 2018 Dustin Morrill, Michael Bowling, and Fatima Davelouis. AI Safety Through Robust Planning. At Alberta Machine Intelligence Institute Tea-time Talk.

Apr 2018 Dustin Morrill. AI Safety Through Robust Planning. At University of British Columbia (hosted by Professor David Poole).

Aug 2014 Dustin Morrill. Regression Counterfactual Regret Minimization. At University of Alberta Reinforcement Learning and Artificial Intelligence Tea-time Talk.

Demonstrations

Oct 2020 Spencer Murray and Dustin Morrill. Applied AI and Poker: DeepStack. At World Summit AI 2020.

Mar 2018 Dustin Morrill. DeepStack exhibition match. At University of Alberta Computing Science Graduate Student’s Association Klatch: Casino Royale.

Feb 2018 Dustin Morrill. Computer poker and DeepStack demonstration. At University of Alberta Department of Computing Science: Reverse Expo.

Jan 2018 Dustin Morrill. Computer poker and DeepStack demonstration. At Telus World of Science: Dark Matters: Game On!.

Feb 2017 Martin Schmid, Dustin Morrill, and Michael Bowling. Play DeepStack on a Commodity Gaming Laptop. At Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17).

Jun 2016 Nolan Bard, Neil Burch, Viliam Lisy, Trevor Davis, Dustin Morrill, and Michael Bowling. Computer poker and Cepheus demonstration (2). At CANHEIT HPCS 2016.

Jun 2016 Nolan Bard, Neil Burch, Viliam Lisy, Trevor Davis, Dustin Morrill, and Michael Bowling. Computer poker and Cepheus demonstration (1). At CANHEIT HPCS 2016.

Dec 2015 Dustin Morrill, Michael Johanson, and Viliam Lisy. Computer poker and Cepheus demonstration. At Telus World of Science: Dark Matters: Game On!.

Jan 2015 Michael Bowling, Robert Holte, Michael Johanson, Neil Burch, Nolan Bard, Dustin Morrill, and Trevor Davis. Computer poker and Cepheus demonstration (2). At AAAI-15 Games Showcase.

Jan 2015 Michael Bowling, Robert Holte, Michael Johanson, Neil Burch, Nolan Bard, Dustin Morrill, and Trevor Davis. Computer poker and Cepheus demonstration (1). At AAAI-15 Games Showcase.

Jan 2015 Michael Bowling, Robert Holte, Michael Johanson, Neil Burch, Nolan Bard, Dustin Morrill, and Trevor Davis. Computer poker and Cepheus demonstration. At AAAI-15 Open House.

Sep 2014 Michael Bowling, Dustin Morrill, and Trevor Davis. Computer poker demonstration. At University of Alberta computing science department’s 50th anniversary open house.

Jul 2013 Dustin Morrill. The Annual Computer Poker Competition Poker Graphical User Interface. At Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI-13).

Videos

Jul 2021 Dustin Morrill, Ryan D’Orazio, Marc Lanctot, James R. Wright, Michael Bowling, and Amy Greenwald. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. At Thirty-Eighth International Conference on Machine Learning (ICML 2021).

Feb 2021 Dustin Morrill, Ryan D’Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, and Michael Bowling. Hindsight and Sequential Rationality of Correlated Play. At Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21).

May 2017 Bryan Paris, Michael Johanson, Nolan Bard, and Dustin Morrill. DeepStack Plays Poker Against Bryan Paris on Twitch.tv. At Twitch.tv.

Apr 2017 Taylor von Kriegenbergh, Michael Johanson, Nolan Bard, and Dustin Morrill. DeepStack Plays Poker Against Taylor von Kriegenbergh on Twitch.tv. At Twitch.tv.

Apr 2017 Dutch Boyd, Michael Johanson, Nolan Bard, and Dustin Morrill. DeepStack Plays Poker Against Dutch Boyd on Twitch.tv. At Twitch.tv.

Apr 2017 Adam Schwartz, Terrence Chan, Michael Johanson, Nolan Bard, and Dustin Morrill. DeepStack Plays Poker Against the 2+2 Pokercast on Twitch.tv. At Twitch.tv.

Mar 2017 Andrew Brokos, Nate Meyvis, Michael Johanson, Nolan Bard, Dustin Morrill, and Michael Bowling. DeepStack Plays Poker Against the Thinking Poker Podcast on Twitch.tv. At Twitch.tv.

Podcasts

Aug 2017 Adam Schwartz, Terrence Chan, and Dustin Morrill. TwoPlusTwo Pokercast—Episode 471. At pokercast.twoplustwo.com.

Aug 2017 Andrew Brokos, Nate Meyvis, Michael Bowling, and Dustin Morrill. Thinking Poker Podcast—Episode 225: Taking the Variance out of Poker. At thinkingpoker.net.

Apr 2017 Andrew Brokos, Nate Meyvis, Michael Johanson, and Dustin Morrill. Thinking Poker Podcast—Episode 210: Michael Johanson and Dustin Morrill. At thinkingpoker.net.

Academic Service

Conference Reviewing

M2026 JMLR

W2024 TMLR

W2023 TMLR

F2022 NeurIPS

F2021 NeurIPS

F2020 NeurIPS (top 10% reviewer)

M2020 ICML (special thanks)

S2019 ICML (top 5% reviewer)

S2019 AAMAS (subreviewer)

F2016 AAMAS (subreviewer)

Workshop Reviewing

W2021 AAAI-RLG

W2020 AAAI-RLG

Teaching

W2016 CMPUT 275 (Introduction to Tangible Computing II), University of Alberta

Part-Time Teaching Assistant

F2015 CMPUT 101 (Introduction to Computing), University of Alberta

Full-Time Teaching Assistant

W2014 CMPUT 175 (Introduction to the Foundations of Computing II), University of Alberta

Full-Time Teaching Assistant

Projects

2017 Computer Poker Research Group Website (http://poker.cs.ualberta.ca/)

2017 Play DeepStack Web Application

2015 Play Cepheus Web Application (http://poker-play.srv.ualberta.ca/)

2011 Various Open-Source Projects (https://github.com/dmorrill10)

2011 ACPC Poker GUI Client (https://github.com/dmorrill10/acpc_poker_gui_client)

Accolades

2021 Alberta Graduate Excellence Scholarship (AGES) ($12,000)

2016 Science Graduate Scholarship ($2000)

2016 CIFAR Deep Learning Summer School 2016 Travel Grant ($500)

2016 Alberta Innovates Graduate Student Scholarship (Doctoral) ($36,000)

2016 NSERC Postgraduate Scholarship–Doctorate Program Award ($63,000)

2016 President’s Doctoral Prize of Distinction ($21,500)

2014 Walter H Johns Graduate Fellowship ($5433.84)

2014 Winning submission, 3-player Kuhn poker competition, 2014 Annual Computer Poker Competition

2014 AITF ICT (Masters) ($12,000)

2014 Alexander Graham Bell Canada Graduate Scholarship - Master’s (NSERC) ($17,500)

2013 NSERC Undergraduate Student Research Award ($6000)

2011 Jason Lang Scholarship ($1000)

2011 Amdahl Academic Achievement Scholarship in Computing Science ($1750)

2010 Jason Lang Scholarship ($1000)

2010 Barry J Mailloux Prize in Computing Science ($1350)

2010 NSERC Undergraduate Student Research Award ($6000)

2009 Jason Lang Scholarship ($1000)

2008 Alexander Rutherford High School Achievement Scholarship ($2500)

2008 Barrhead Minor Hockey Association Scholarship ($500)

2008 Robert Tegler Entrance Scholarship ($2500)

2008 Stuart Olson Faculty of Science Rising Star Entrance Scholarship ($1000)

Personal Information

Last updated: Jul 16, 2026