Sam Ganzfried


Comedy

I wrote several sketches as assignments for the Sketch Writing Basics course at Upright Citizens Brigade Training Center.


Sam Ganzfried. 2016. 10-20. One-page intro of new sketch.


Sam Ganzfried. 2016. Improv "101".


Sam Ganzfried. 2016. Small Melon. Advertisement assignment.


Sam Ganzfried. 2016. Nurse Scheduler.

Sam Ganzfried. 2016. Superbowl. Audio version performed by Andrew Mooers and Pearl Shin.

I am an assistant professor in the School of Computing and Information Sciences at Florida International University, where I am the director of the Strategic Adversarial Multiagent Artificial Intelligence Lab (SAM AI).

I am teaching a new Game Theory course (CAP-5993/4993) in spring 2017 (students enrolled from computer science, statistics, bioinformatics, and electrical and computer engineering departments). See the first lecture here. Here are slides providing an overview of my research from the recent SCIS Information Session. 


I have a PhD in computer science from Carnegie Mellon University and A.B. in math from Harvard University (see my CV here).  I'm interested in artificial intelligence, game theory, multiagent systems, multiagent learning, large-scale optimization, large-scale data analysis and analytics, and knowledge representation. See my research statement for elaboration. My dissertation was on scalable approaches for computing game-theoretic solution concepts and learning in imperfect-information games. Here are slides from my thesis defense that also provide an overview of several topics of active study in multiagent systems and computational game theory.


I created the two-player no-limit Texas hold 'em agent Claudico that competed in the Brains vs. Artificial Intelligence Competition against the strongest human players. See my paper, slides, and video presentation (starting at 1:33). Here is a thread on the Two Plus Two Forum, the most popular poker forum, discussing the event (the thread has over 230,000 views). I describe Claudico's key strengths and weaknesses and address several common questions in this post. See Claudico in action against Doug Polk (widely regarded as the best two-player no-limit Texas hold 'em player in the world) here. I also created the agent Tartanian7 that came in first place in the Annual Computer Poker Competition, beating each opposing agent with statistical significance. A brief description I wrote is available here, and a full description is provided in my paper below. I describe the design of the agent and the current state of research in computer poker in detail in this thread on the Two Plus Two Forum. The Brains vs. Artificial Intelligence Competition was organized by Professor Tuomas Sandholm. Collaborators on Claudico and Tartanian7 were Tuomas Sandholm and Noam Brown.


For takeaways and future directions, see the final chapter of my thesis, the final section of my paper on the Brains vs. Artificial Intelligence Competition, and slides from a talk I gave last year to the Princeton Poker Club. See also slides from my talk at Stanford which includes discussion of how Libratus improved on Claudico and slides from my more recent talk in Einstein's lecture hall at Princeton on the surprising breakthrough that enabled superhuman two-player no-limit Texas hold 'em play.

 
I organized the first ever tutorial on Computer Poker with Marc Lanctot from Google DeepMind at the 2016 Conference on Economics and Computation (7/25/2016). See my slides from part 1 and Marc's from part 2. I organized the AAAI-15 Workshop on Computer Poker and Imperfect Information and co-organized it in 2014 with Eric Jackson. Here is a report summarizing the highlights of the most recent workshop. I have been a PC member for AAAI (2012, 2014, 2015, 2016, 2017), AAMAS (2014, 2016), and IJCAI (2013, 2015, 2016).


I organized the second Computer Poker Tutorial with Johannes Heinrich and Kevin Waugh at AAAI 2017. Here are slides from part 1, part 2, and part 3. Here is a livestream broadcast of my portion: first half, second half.


See also recent articles from the Pittsburgh Tribune-Review and front page of the "Tropical Life" section of the Miami Herald, and my tv debut as "The Robot"  and subsequent commentary on Poker Night in America.


Working Papers


Sam Ganzfried and Farzana Yusuf. Computing Human-Understandable Strategies. arXiv.

Early version in Proceedings of the Workshop on Computer Poker and Imperfect Information Games at AAAI Conference on Artificial Intelligence (AAAI), 2017.


Sam Ganzfried. Optimal Number of Choices in Rating Contexts. arXiv. To appear in Workshop and Conference Proceedings series of the Journal of Machine Learning Research (JMLR). Poster spotlight presentation at Workshop on Imperfect Decision Makers: Admitting Real-World Rationality at Conference on Neural Information Processing Systems (NIPS), 2016 (slides). INFORMS poster was finalist in poster competition.


Sam Ganzfried and Qingyun Sun. Bayesian Opponent Exploitation in Imperfect-Information Games. arXiv. UECE Lisbon Meetings in Game Theory and Applications presentation slides.


Publications


Sam Ganzfried. 2015. Reflections on the First Man vs. Machine No-Limit Texas Hold 'em Competition. SIGecom Exchanges, Volume 14.2. Feature article. Earlier version from September 2015. Slides from presentation at 2016 World Congress of the Game Theory Society (7/24/2016) and slides/video (starting at 1:33) from presentation at 2016 New York Computer Science and Economics Day (1/29/2016).


Sam Ganzfried. 2015. Computing Strong Game-Theoretic Strategies and Exploiting Suboptimal Opponents in Large Games. PhD dissertation, Computer Science Department, Carnegie Mellon University. Available as CMU technical report CMU-CS-15-104.

Sam Ganzfried and Tuomas Sandholm. 2015.
Endgame Solving in Large Imperfect-Information Games. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Early version appeared in Proceedings of the Workshop on Computer Poker and Imperfect Information at the AAAI Conference on Artificial Intelligence (AAAI), 2013. The best two-player no-limit Texas hold 'em player in the world (Doug Polk) stated that the "endgame solver" was the strongest component of the agent Claudico in the Brains vs. Artificial Intelligence Competition. The approach has been subsequently adopted by popular commercial software such as GTORangeBuilder and PioSOLVER, and extensions of the paradigm introduced in this work were crucial to the success of the recent agents DeepStack and Libratus. The leader of DeepStack has stated that "Deepstack is all endgame solving," and the strongest component of Libratus was an improved endgame solving approach that enabled solving both the turn and river rounds (as opposed to just the river) in real time on a supercomputer.

Noam Brown*, Sam Ganzfried*, and Tuomas Sandholm. 2015. Hierarchical Abstraction, Distributed Equilibrium Computation, and Post-Processing, with Application to a Champion No-Limit Texas Hold'em Agent. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Short version appeared in Proceedings of the Demonstrations Program at the AAAI Conference on Artificial Intelligence (AAAI), 2015. *Listed alphabetically. Describes the architecture of two-player no-limit Texas hold 'em agent Tartanian7, which won the 2014 AAAI Annual Computer Poker Competition.

Sam Ganzfried and Tuomas Sandholm. 2015. Safe Opponent Exploitation. ACM Transactions on Economics and Computation (TEAC), 3(2), 8:1-28. Special issue on selected papers from EC-12. Algorithms and theoretical analysis for when it is possible to deviate from just repeatedly playing one-shot equilibrium to exploit opponents' weaknesses.

Sam Ganzfried and Tuomas Sandholm. 2014. Potential-Aware Imperfect-Recall Abstraction with Earth Mover's Distance in Imperfect-Information Games. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). Algorithm for game abstraction that takes into account trajectories of private information revelation across all rounds. See discussion on Poker-AI forum.

Sam Ganzfried. 2013. Computing Strong Game-Theoretic Strategies and Exploiting Suboptimal Opponents in Large Games. Thesis proposal.

Sam Ganzfried and Tuomas Sandholm. 2013. Action Translation in Extensive-Form Games with Large Action Spaces: Axioms, Paradoxes, and the Pseudo-Harmonic Mapping. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). Algorithm for interpreting opponents' actions that have been removed from game abstraction, which is used by strongest no-limit Texas hold 'em agents.

Sam Ganzfried and Tuomas Sandholm. 2012. Tartanian5: A Heads-Up No-Limit Texas Hold'em Poker-Playing Program. In Proceedings of the Computer Poker Symposium at the AAAI Conference on Artificial Intelligence (AAAI).

Sam Ganzfried and Tuomas Sandholm. 2012. Safe Opponent Exploitation. In Proceedings of the ACM Conference on Electronic Commerce (EC). Succeeded by TEAC paper listed above.

Sam Ganzfried, Tuomas Sandholm, and Kevin Waugh. 2012. Strategy Purification and Thresholding: Effective Non-Equilibrium Approaches for Playing Large Games. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Theory and experiments for techniques for post-processing approximate equilibrium strategies of game abstractions.

Sam Ganzfried. 2011. Computing Strong Game-Theoretic Strategies in Jotto. In Proceedings of the Conference on Advances in Computer Games (ACG). Algorithm and experiments for computing game-theoretic strategies in the game Jotto.

Sam Ganzfried and Tuomas Sandholm. 2011. Game Theory-Based Opponent Modeling in Large Imperfect-Information Games. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Algorithm integrates approximate equilibrium prior with learning from observations and does not require historical data or domain-specific features.

Sam Ganzfried and Tuomas Sandholm. 2010. Computing Equilibria by Incorporating Qualitative Models. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Extended version appeared as CMU technical report CMU-CS-10-105. Algorithm exploits human-understandable qualitative strategy model to improve equilibrium-finding in class of Bayesian games with application to limit Texas hold 'em. 

Sam Ganzfried and Tuomas Sandholm. 2009. Computing Equilibria in Multiplayer Stochastic Games of Imperfect Information. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI). New algorithm with theoretical results for computing approximate Nash equilibrium in multiplayer stochastic imperfect-information games with application to realistic three-player poker tournament.

Sam Ganzfried and Tuomas Sandholm. 2008. Computing an Approximate Jam/Fold Equilibrium for 3-Player No-Limit Texas Hold'em Tournaments. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Algorithm computes approximate Nash equilibrium in multiplayer stochastic imperfect-information games, with application to a realistic three-player poker tournament. Similar approach has been subsequently adopted by popular commercial software such as HoldemResources.


Sam Ganzfried. 2005. Computing Nash Equilibria in Two-Player Strategic-Form Games. Senior thesis at Harvard University for honors in Mathematics. Note that this is an expository survey article and not an original research paper (see page 4 here). Much of it is adapted from other works. For example, the discussion on linear complementarity and the Lemke-Howson Algorithm is drawn from this article.

Sam Ganzfried. 2004. A New Algorithm for Knight's Tours. In Proceedings of the Research Experiences for Undergraduates Program in Mathematics.