General video game playing escapes the no free lunch theorem

Popular topics in current research within the games community are general game playing and general video game playing. Both of these efforts seek to find relatively general purpose AI to play games. Within the optimization community we are approaching the 20th anniversary of the no free lunch theorem. In this paper we suggest reasons why a games version of a no free lunch result is probably not problematic. This is accomplished by noting that none of the "general" efforts are - or should be - actually general. Technology is proposed to exploit the lack of generality to permit more effective game playing AIs to be designed. A program for classifying games is outlined that consists of gathering performance data on many games for many algorithms and then using the resulting matrix of performance data to create a tree structured classification of the games. This classification is proposed as the basis for assigning games to appropriate algorithms within a more general framework. A novel algorithm that yields more stable tree-based classification is also proposed.

[1]  Daniel A. Ashlock,et al.  Graph-based evolutionary algorithms , 2006, IEEE Transactions on Evolutionary Computation.

[2]  Jens Lienig,et al.  A parallel genetic algorithm for performance-driven VLSI routing , 1997, IEEE Trans. Evol. Comput..

[3]  Michael L. Littman,et al.  Bandit-Based Planning and Learning in Continuous-Action Markov Decision Processes , 2012, ICAPS.

[4]  Mark H. M. Winands,et al.  N-Grams and the Last-Good-Reply Policy Applied in General Game Playing , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[5]  Simon M. Lucas,et al.  Population seeding techniques for Rolling Horizon Evolution in General Video Game Playing , 2017, 2017 IEEE Congress on Evolutionary Computation (CEC).

[6]  Dennis J. N. J. Soemers,et al.  Enhancements for real-time Monte-Carlo Tree Search in General Video Game Playing , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[7]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[8]  Simon M. Lucas,et al.  Multi-objective tree search approaches for general video game playing , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[9]  Julian Togelius,et al.  General Video Game AI: Competition, Challenges and Opportunities , 2016, AAAI.

[10]  Kyungsook Han,et al.  Finding motif pairs in the interactions between heterogeneous proteins via bootstrapping and boosting , 2009, BMC Bioinformatics.

[11]  Cameron McGuinness.  Classification of Monte Carlo tree search variants , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[12]  Julian Togelius,et al.  Search-Based Procedural Content Generation , 2010, EvoApplications.

[13]  Daniel Ashlock,et al.  Breaking a Hierarchical Clustering Algorithm with an Evolutionary Algorithm , 2009 .

[14]  Julian Togelius,et al.  Towards Procedural Strategy Game Generation: Evolving Complementary Unit Types , 2011, EvoApplications.

[15]  Tom Schaul,et al.  An Extensible Description Language for Video Games , 2014, IEEE Transactions on Computational Intelligence and AI in Games.

[16]  Eun-Youn Kim,et al.  Understanding representational sensitivity in the iterated prisoner's dilemma with fingerprints , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[17]  Daniel A. Ashlock,et al.  A discrete representation for real optimization with unique search properties , 2014, 2014 IEEE Symposium on Foundations of Computational Intelligence (FOCI).

[18]  Hector Geffner,et al.  Width-Based Planning for General Video-Game Playing , 2015, AIIDE.

[19]  Michael R. Genesereth,et al.  General Game Playing: Overview of the AAAI Competition , 2005, AI Mag..

[20]  Daniel A. Ashlock,et al.  Test problems and representations for graph evolution , 2014, 2014 IEEE Symposium on Foundations of Computational Intelligence (FOCI).

[21]  Sander Bakkes,et al.  Monte Carlo Tree Search with options for general video game playing , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[22]  Johannes Fürnkranz,et al.  Informed Hybrid Game Tree Search , 2016 .

[23]  Julian Togelius,et al.  Hyper-heuristic general video game playing , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[24]  Simon M. Lucas,et al.  General Video Game for 2 players: Framework and competition , 2016, 2016 8th Computer Science and Electronic Engineering (CEEC).

[25]  Daniel A. Ashlock,et al.  MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering , 2009, BMC Bioinformatics.

[26]  Simon M. Lucas,et al.  Knowledge-based fast evolutionary MCTS for general video game playing , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[27]  Julian Togelius,et al.  Ieee Transactions on Computational Intelligence and Ai in Games the 2014 General Video Game Playing Competition , 2022 .

[28]  Sanaz Mostaghim,et al.  Procedural level generation with answer set programming for general Video Game playing , 2015, 2015 7th Computer Science and Electronic Engineering Conference (CEEC).

[29]  Annie Louis,et al.  Beyond playing to win: Diversifying heuristics for GVGAI , 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG).

[30]  Mark H. M. Winands,et al.  Enhancements for Multi-Player Monte-Carlo Tree Search , 2010, Computers and Games.

[31]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[32]  R. Sokal,et al.  Numerical Taxonomy: The Principles and Practice of Numerical Classification. , 1975 .

[33]  Julian Togelius,et al.  Investigating MCTS modifications in general video game playing , 2015, 2015 IEEE Conference on Computational Intelligence and Games (CIG).

[34]  Simon M. Lucas,et al.  Rolling horizon evolution enhancements in general video game playing , 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG).

[35]  Julian Togelius,et al.  Matching Games and Algorithms for General Video Game Playing , 2021, AIIDE.

[36]  Mike Preuss,et al.  MCTS/EA hybrid GVGAI players and game difficulty estimation , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[37]  Simon M. Lucas,et al.  Rolling horizon evolution versus tree search for navigation in single-player real-time games , 2013, GECCO '13.

[38]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[39]  Bernard M. E. Moret,et al.  Phylogenetic Inference , 2011, Encyclopedia of Parallel Computing.

[40]  W. Rudin.  Principles of mathematical analysis , 1964 .