Extensive-form game abstraction with bounds

Abstraction has emerged as a key component in solving extensive-form games of incomplete information. However, lossless abstractions are typically too large to solve, so lossy abstraction is needed. All prior lossy abstraction algorithms for extensive-form games either 1) had no bounds on solution quality or 2) depended on specific equilibrium computation approaches, limited forms of abstraction, and only decreased the number of information sets rather than nodes in the game tree. We introduce a theoretical framework that can be used to give bounds on solution quality for any perfect-recall extensive-form game. The framework uses a new notion for mapping abstract strategies to the original game, and it leverages a new equilibrium refinement for analysis. Using this framework, we develop the first general lossy extensive-form game abstraction method with bounds. Experiments show that it finds a lossless abstraction when one is available and lossy abstractions when smaller abstractions are desired. While our framework can be used for lossy abstraction, it is also a powerful tool for lossless abstraction if we set the bound to zero. Prior abstraction algorithms typically operate level by level in the game tree. We introduce the extensive-form game tree isomorphism and action subset selection problems, both important problems for computing abstractions on a level-by-level basis. We show that the former is graph isomorphism complete, and the latter NP-complete. We also prove that level-by-level abstraction can be too myopic and thus fail to find even obvious lossless abstractions.

[1]  R. C. Sprinthall Basic Statistical Analysis , 1982 .

[2]  R. Varga,et al.  Proof of Theorem 4 , 1983 .

[3]  Richard S. Varga,et al.  Proof of Theorem 5 , 1983 .

[4]  Leonard M. Adleman,et al.  Proof of proposition 3 , 1992 .

[5]  D. Koller,et al.  Efficient Computation of Equilibria for Extensive Two-Person Games , 1996 .

[6]  Paul Resnick,et al.  Recommender systems , 1997, CACM.

[7]  B. Peleg,et al.  The canonical extensive form of a game form: symmetries , 1999 .

[8]  Loriene Roy,et al.  Content-based book recommending using learning for text categorization , 1999, DL '00.

[9]  Kaname Funakoshi,et al.  A content-based collaborative recommender system with detailed use of evaluations , 2000, KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings (Cat. No.00TH8516).

[10]  Michael L. Littman,et al.  Abstraction Methods for Game Theoretic Poker , 2000, Computers and Games.

[11]  Ian Frank,et al.  Revised Papers from the Second International Conference on Computers and Games , 2000 .

[12]  M. Newman,et al.  Random graphs with arbitrary degree distributions and their applications. , 2000, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[14]  Jonathan Schaeffer,et al.  Approximating Game-Theoretic Optimal Strategies for Full-scale Poker , 2003, IJCAI.

[15]  Peter Stone,et al.  A polynomial-time nash equilibrium algorithm for repeated games , 2003, EC '03.

[16]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[17]  Aranyak Mehta,et al.  Playing large games using simple strategies , 2003, EC '03.

[18]  Thomas Hofmann,et al.  Latent semantic models for collaborative filtering , 2004, TOIS.

[19]  Joseph A. Konstan,et al.  Introduction to recommender systems: Algorithms and Evaluation , 2004, TOIS.

[20]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[21]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[22]  Yevgeniy Dodis,et al.  Entropic Security and the Encryption of High Entropy Messages , 2005, TCC.

[23]  Tuomas Sandholm,et al.  A Competitive Texas Hold'em Poker Player via Automated Abstraction and Real-Time Equilibrium Computation , 2006, AAAI.

[24]  Tuomas Sandholm,et al.  Finding equilibria in large sequential games of imperfect information , 2006, EC '06.

[25]  M. A. Sasse,et al.  ’Knowing me, knowing you’ — Using profiles and social networking to improve recommender systems , 2006 .

[26]  Michael J. Pazzani,et al.  Content-Based Recommendation Systems , 2007, The Adaptive Web.

[27]  Tuomas Sandholm,et al.  Better automated abstraction techniques for imperfect information games, with application to Texas Hold'em poker , 2007, AAMAS '07.

[28]  Maarten de Rijke,et al.  Extracting the discussion structure in comments on news-articles , 2007, WIDM '07.

[29]  Tuomas Sandholm,et al.  Lossless abstraction of imperfect information games , 2007, JACM.

[30]  Hsinchun Chen,et al.  A Comparison of Collaborative-Filtering Recommendation Algorithms for E-commerce , 2007, IEEE Intelligent Systems.

[31]  Dan Frankowski,et al.  Collaborative Filtering Recommender Systems , 2007, The Adaptive Web.

[32]  Troels Bjerre Lund,et al.  Potential-Aware Automated Abstraction of Sequential Games, and Holistic Equilibrium Analysis of Texas Hold'em Poker , 2007, AAAI.

[33]  Michael H. Bowling,et al.  Regret Minimization in Games with Incomplete Information , 2007, NIPS.

[34]  Troels Bjerre Lund,et al.  A heads-up no-limit Texas Hold'em poker player: discretized betting models and automatically generated equilibrium-finding programs , 2008, AAMAS.

[35]  Michael H. Bowling,et al.  Probabilistic State Translation in Extensive Games with Large Action Sets , 2009, IJCAI.

[36]  Kevin Waugh,et al.  A Practical Use of Imperfect Recall , 2009, SARA.

[37]  Ofer Arazy,et al.  Improving Social Recommender Systems , 2009, IT Professional.

[38]  Kevin Waugh,et al.  Abstraction pathologies in extensive games , 2009, AAMAS.

[39]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[40]  Wesley W. Chu,et al.  A Social Network-Based Recommender System (SNRS) , 2010, Data Mining for Social Network Data.

[41]  Yehuda Koren,et al.  Factor in the neighbors: Scalable and accurate collaborative filtering , 2010, TKDD.

[42]  Tuomas Sandholm,et al.  The State of Solving Large Incomplete-Information Games, and Application to Poker , 2010, AI Mag..

[43]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[44]  Maria J. Serna,et al.  The complexity of game isomorphism , 2011, Theor. Comput. Sci..

[45]  Duane Szafron,et al.  Automated Action Abstraction of Imperfect Information Extensive-Form Games , 2011, AAAI.

[46]  Chao Liu,et al.  Recommender systems with social regularization , 2011, WSDM '11.

[47]  Nicola Basilico,et al.  Automated Abstractions for Patrolling Security Games , 2011, AAAI.

[48]  Ashwin Machanavajjhala,et al.  Personalized Social Recommendations - Accurate or Private? , 2011, Proc. VLDB Endow..

[49]  Kevin Leyton-Brown,et al.  Polynomial-time computation of exact correlated equilibrium in compact games , 2010, EC '11.

[50]  Michael H. Bowling,et al.  No-Regret Learning in Extensive-Form Games with Imperfect Recall , 2012, ICML.

[51]  Fei Wang,et al.  Social contextual recommendation , 2012, CIKM.

[52]  Yehuda Koren,et al.  Care to comment?: recommendations for commenting on news stories , 2012, WWW.

[53]  Tuomas Sandholm,et al.  Lossy stochastic game abstraction with bounds , 2012, EC '12.

[54]  Duane Szafron,et al.  Using Sliding Windows to Generate Action Abstractions in Extensive-Form Games , 2012, AAAI.

[55]  Chun Chen,et al.  An exploration of improving collaborative recommender systems via user-item subgroups , 2012, WWW.

[56]  David Gross-Amblard,et al.  Discovering implicit communities in Web forums through ontologies , 2012, Web Intell. Agent Syst..

[57]  Di Ma,et al.  Incorporating Social Actions into Recommender Systems , 2013, WAIM.

[58]  Giuseppe Persiano,et al.  Special Issue on Algorithmic Game Theory , 2013, Theory of Computing Systems.

[59]  Michael H. Bowling,et al.  Evaluating state-space abstractions in extensive-form games , 2013, AAMAS.

[60]  Tuomas Sandholm,et al.  Action Translation in Extensive-Form Games with Large Action Spaces: Axioms, Paradoxes, and the Pseudo-Harmonic Mapping , 2013, IJCAI.

[61]  Hwan-Gue Cho,et al.  Detecting and visualizing online dispute dynamics in replying comments , 2013, Softw. Pract. Exp..

[62]  Wenwu Zhu,et al.  Scalable Recommendation with Social , 2014 .

[63]  Tuomas Sandholm,et al.  Potential-Aware Imperfect-Recall Abstraction with Earth Mover's Distance in Imperfect-Information Games , 2014, AAAI.

[64]  Tuomas Sandholm,et al.  Regret Transfer and Parameter Optimization , 2014, AAAI.