Extending Specialized Systems to a Generic Approach of Game Playing

Vaibhav Kataria¹

Section:Research Paper, Product Type: Isroset-Journal
Vol.6 , Issue.6 , pp.31-34, Dec-2018

CrossRef-DOI:   https://doi.org/10.26438/ijsrcse/v6i6.3134

Online published on Dec 31, 2018

Copyright © Vaibhav Kataria . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

519 Views    284 Downloads    169 Downloads

Abstract :
Better decision making requires better analysis of the situation at hand. A program which can analyze the current situation better, can take better decisions, thus, increasing the likelihood of winning more games. Specialized game players are very narrow. They might outperform humans in a particular game and know nothing about any other game. They do only part of the work. Most of the definition, analysis and design is done in backend, within the systems by their programmers. Generic Game Bot are systems which are able to accept descriptions of any game at runtime and can use such definitions to play that game effectively, without any human intervention or supervision, i.e., they do not know the rules of the games beforehand. Generic Bot as such should be capable of playing simple games (like Snake) and complex games (like Chess), games in static or dynamic environments, games with complete and partial information, games with different numbers of players, with simultaneous or alternating turn of play, with or without communication among the players, and so forth.

Key-Words / Index Term :
General Game Playing; Specialized Systems; Game Bot; Reinforcement Learning; Classification of Games; OpenAI; Generic game Player; Game Description Language

References :
[1] M. Swiechowski & J. Mandziuk, “Specialized vs. Multi-game Approaches to AI in Games”, Proceedings of the 7th IEEE International Conference on Intelligent Systems, pp. 243-254,2014
[2] S. Schiffel & M. Thielscher “Representing and Reasoning About the Rules of General Games With Imperfect Information”, Journal of Artificial Intelligence Research Vol. 49, pp. 171-206 , 2014
[3] J. Romero, A. Saffidine & M. Thielscher, “Solving the Inferential Frame Problem in the General Game Description Language”, Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence,2014.
[4] M. Genesereth & M. Thielscher, “General Game Playing”, 2014
[5] M. Swiechowski & J. Mandziuk, “Self-Adaptation of Playing Strategies in General Game Playing”, Computational Intelligence and AI in Games, IEEE Transactions on Vol. PP(99), 2013
[6] A. Saffidine, H. Finnsson & M. Buro, “Alpha-Beta Pruning for Games with Simultaneous Moves”, The Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012
[7] S. Haufe, S. Schiffel & M. Thielscher, “Automated Verification of State Sequence Invariants in General Game Playing”, Artificial Intelligence Vol. 187-188, pp. 1-30 , 2012
[8] H. Finnsson, “Simulation-Based General Game Playing”, PhD Thesis Reykjavík University, 2012
[9] X. Sheng & D. Thuente, “Using Decision Trees for State Evaluation in General Game Playing”, KI Vol. 25(1), pp. 53-56, 2011