General Language Evolution in General Game Playing

General Game Playing (GGP) is concerned with the development of programs capable of expertly playing a game by just receiving its rules and without human intervention. Its standard Game Description Language (GDL) has been extended so as to include incomplete information games. The extended version is named as GDL-II. Different algorithms were recommended to play games in GDL-II, however, none of them can solve coordination games properly. One reason for this shortcoming is their inability to generate the necessary coordination language. On the other side, most existing language evolution techniques focus on generating a common language without considering its generality or its use for problem solving. In this paper, we will extend GGP with language evolution to develop a general language generation technique. The new technique can be combined with GGP algorithms for incomplete-information games and assist players in automatically generating a common language to solve cooperation problems.

[1]  Luc Steels,et al.  Language games for autonomous robots , 2001 .

[2]  Michael Thielscher,et al.  Lifting Model Sampling for General Game Playing to Incomplete-Information Models , 2015, AAAI.

[3]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[4]  Luc Steels.  A self-organizing spatial vocabulary , 1995 .

[5]  Richard A. Watson,et al.  Minimally Sufficient Conditions for the Evolution of Social Learning and the Emergence of Non-Genetic Evolutionary Systems , 2017, Artificial Life.

[6]  Luc Steels,et al.  The Grounded Colour Naming Game , 2009 .

[7]  Sarit Kraus,et al.  Coordination without Communication: Experimental Validation of Focal Point Techniques , 1997, ICMAS.

[8]  Craig Boutilier,et al.  Sequential Optimality and Coordination in Multiagent Systems , 1999, IJCAI.

[9]  Marjorie Skubic,et al.  Spatial language for human-robot dialogs , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[10]  Michael Thielscher,et al.  Iterative Tree Search in General Game Playing with Incomplete Information , 2018, CGW@IJCAI.

[11]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[12]  Moshe Tennenholtz,et al.  Bundling equilibrium in combinatorial auctions , 2002, Games Econ. Behav..

[13]  Luc Steels,et al.  Can Body Language Shape Body Image? , 2008, ALIFE.

[14]  Shimon Whiteson,et al.  Learning to Communicate with Deep Multi-Agent Reinforcement Learning , 2016, NIPS.

[15]  L. Steels,et al.  Crucial factors in the origins of word-meaning , 2000 .

[16]  Luc Steels,et al.  Aibo''s first words. the social learning of language and meaning. Evolution of Communication , 2002 .

[17]  Thomas Keller,et al.  Past, Present, and Future: An Optimal Online Algorithm for Single-Player GDL-II Games , 2014, ECAI.

[18]  Michael Thielscher,et al.  A General Game Description Language for Incomplete Information Games , 2010, AAAI.