Difference between revisions of "General Game Playing"

From Chessprogramming wiki
Jump to: navigation, search
 
(12 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
'''[[Main Page|Home]] * [[Games]] * General Game Playing'''
 
'''[[Main Page|Home]] * [[Games]] * General Game Playing'''
  
'''General Game Playing''',<br/>
+
'''General Game Playing''', (GGP)<br/>
 
an approach of Artificial Intelligence programs to be able to play more than one game successfully. For games like [[Chess|chess]], computers are programmed to play these games using a specially designed algorithm - a chess playing program cannot play [[Checkers|checkers]]. A General Game Playing system, if well designed, would be able to help in other areas, such as in providing intelligence for search and rescue missions <ref>[http://www.general-game-playing.de/ General Game Playing - Home]</ref>. One well know commercial General Game program is [[Zillions of Games]] by [[Jeff Mallett]] and [[Mark Lefler]] <ref>[https://en.wikipedia.org/wiki/Zillions_of_Games Zillions of Games from Wikipedia]</ref> .
 
an approach of Artificial Intelligence programs to be able to play more than one game successfully. For games like [[Chess|chess]], computers are programmed to play these games using a specially designed algorithm - a chess playing program cannot play [[Checkers|checkers]]. A General Game Playing system, if well designed, would be able to help in other areas, such as in providing intelligence for search and rescue missions <ref>[http://www.general-game-playing.de/ General Game Playing - Home]</ref>. One well know commercial General Game program is [[Zillions of Games]] by [[Jeff Mallett]] and [[Mark Lefler]] <ref>[https://en.wikipedia.org/wiki/Zillions_of_Games Zillions of Games from Wikipedia]</ref> .
 +
 +
=GVGP=
 +
General video game playing (GVGP) is the concept of GGP adjusted to the purpose of playing [https://en.wikipedia.org/wiki/Video_game video games]  <ref>[https://en.wikipedia.org/wiki/General_video_game_playing General video game playing from Wikipedia]</ref>, and to apply [[Reinforcement Learning|reinforcement learning]] and [[Monte-Carlo Tree Search|Monte-Carlo tree search]] to master video and [[Atari 8-bit|Atari]] games of skill and strategy.
  
 
=Selected Publications=  
 
=Selected Publications=  
Line 27: Line 30:
 
* [[Tomoyuki Kaneko]], [[Kazunori Yamaguchi]], [[Satoru Kawai]] ('''2003'''). ''Automated Identification of Patterns in Evaluation Functions for General Game Players''. [[Advances in Computer Games 10]]
 
* [[Tomoyuki Kaneko]], [[Kazunori Yamaguchi]], [[Satoru Kawai]] ('''2003'''). ''Automated Identification of Patterns in Evaluation Functions for General Game Players''. [[Advances in Computer Games 10]]
 
==2005 ...==  
 
==2005 ...==  
* [[Michael Genesereth]], [http://dblp.uni-trier.de/pers/hd/l/Love:Nathaniel Nathaniel Love], [[Barney Pell]] ('''2005'''). ''General Game Playing: Overview of the AAAI Competition''. [[AAAI#AIMAG|AI Magazine]], Vol. 26, No. 2, [http://logic.stanford.edu/classes/cs227/2013/readings/aaai.pdf pdf]  
+
* [[Michael Genesereth]], [[Nathaniel Love]], et al. ('''2005'''). ''General Game Playing: Game Description Language Specification''. Technical report, [[Stanford University]]
 +
* [[Michael Genesereth]], [[Nathaniel Love]], [[Barney Pell]] ('''2005'''). ''General Game Playing: Overview of the AAAI Competition''. [[AAAI#AIMAG|AI Magazine]], Vol. 26, No. 2, [http://logic.stanford.edu/classes/cs227/2013/readings/aaai.pdf pdf]  
 
* [[Michael Thielscher]] ('''2005'''). ''Flux: A logic programming method for reasoning agents''. [http://www.informatik.uni-trier.de/~ley/db/journals/tplp/tplp5.html#Thielscher05 Theory Pract.Log. Program, 5(4-5)]
 
* [[Michael Thielscher]] ('''2005'''). ''Flux: A logic programming method for reasoning agents''. [http://www.informatik.uni-trier.de/~ley/db/journals/tplp/tplp5.html#Thielscher05 Theory Pract.Log. Program, 5(4-5)]
 
* [[Stephan Schiffel]], [[Michael Thielscher]] ('''2007'''). ''Fluxplayer: A successful general game player''. [http://www.aaai.org/Press/Proceedings/aaai07.php Proceedings of the AAAI National Conference on Artificial Intelligence], [http://www.aaai.org/Papers/AAAI/2007/AAAI07-189.pdf pdf]
 
* [[Stephan Schiffel]], [[Michael Thielscher]] ('''2007'''). ''Fluxplayer: A successful general game player''. [http://www.aaai.org/Press/Proceedings/aaai07.php Proceedings of the AAAI National Conference on Artificial Intelligence], [http://www.aaai.org/Papers/AAAI/2007/AAAI07-189.pdf pdf]
 
* [[Michel Quenault]], [[Tristan Cazenave]] ('''2007'''). ''Extended General Gaming Model''. [[CGW 2007]]
 
* [[Michel Quenault]], [[Tristan Cazenave]] ('''2007'''). ''Extended General Gaming Model''. [[CGW 2007]]
* [[Hilmar Finnsson]] and [[Yngvi Björnsson]]. ('''2008'''). ''Simulation-Based Approach to General Game Playing.'' In The Twenty-Third AAAI Conference on Artificial Intelligence, [[AAAI]] Press, 2008. Accepted. [http://www.ru.is/faculty/yngvi/pdf/FinnssonB08a.pdf pdf], [http://www.aaai.org/Papers/AAAI/2008/AAAI08-041.pdf pdf]
+
* [[James Clune]] ('''2007'''). ''Heuristic Evaluation Functions for General Game Playing''. [[Conferences#AAAI-2007|AAAI 2007]], [https://www.aaai.org/Papers/AAAI/2007/AAAI07-180.pdf pdf]
 +
* [[Joseph Reisinger]], [[Erkin Bahçeci]], [[Igor Karpov]], [[Risto Miikkulainen]] ('''2007'''). ''[https://www.semanticscholar.org/paper/Coevolving-Strategies-for-General-Game-Playing-Reisinger-Bah%C3%A7eci/9a39c1411b6e68457ece391b057dcc26142c23a7 Coevolving Strategies for General Game Playing]''. [https://dblp.uni-trier.de/db/conf/cig/cig2007.html CIG 2007]
 +
* [[Hilmar Finnsson]], [[Yngvi Björnsson]]. ('''2008'''). ''Simulation-Based Approach to General Game Playing.'' In The Twenty-Third AAAI Conference on Artificial Intelligence, [[AAAI]] Press, 2008. Accepted. [http://www.ru.is/faculty/yngvi/pdf/FinnssonB08a.pdf pdf], [http://www.aaai.org/Papers/AAAI/2008/AAAI08-041.pdf pdf]
 
* [[Jean Méhat]], [[Tristan Cazenave]] ('''2008'''). ''Ary: A Program for General Game Playing''. [http://www.lamsade.dauphine.fr/~cazenave/papers/poster2008.pdf pdf]
 
* [[Jean Méhat]], [[Tristan Cazenave]] ('''2008'''). ''Ary: A Program for General Game Playing''. [http://www.lamsade.dauphine.fr/~cazenave/papers/poster2008.pdf pdf]
 
* [[Jean Méhat]], [[Tristan Cazenave]] ('''2008'''). ''Monte-Carlo Tree Search for General Game Playing''. [http://www.lamsade.dauphine.fr/~cazenave/papers/ggp2008.pdf pdf]
 
* [[Jean Méhat]], [[Tristan Cazenave]] ('''2008'''). ''Monte-Carlo Tree Search for General Game Playing''. [http://www.lamsade.dauphine.fr/~cazenave/papers/ggp2008.pdf pdf]
Line 43: Line 49:
 
* [[Karol Walędzik]], [[Jacek Mańdziuk]] ('''2010'''). ''CI in General Game Playing - to date Achievements and Perspectives''. [http://www.informatik.uni-trier.de/~ley/db/conf/icaisc/icaisc2010-2.html#WaledzikM10 10. ICAISC], [http://www.mini.pw.edu.pl/~mandziuk/PRACE/ICAISC10.pdf pdf]
 
* [[Karol Walędzik]], [[Jacek Mańdziuk]] ('''2010'''). ''CI in General Game Playing - to date Achievements and Perspectives''. [http://www.informatik.uni-trier.de/~ley/db/conf/icaisc/icaisc2010-2.html#WaledzikM10 10. ICAISC], [http://www.mini.pw.edu.pl/~mandziuk/PRACE/ICAISC10.pdf pdf]
 
'''2011'''
 
'''2011'''
 +
* [[Michael Thielscher]] ('''2011'''). ''The General Game Playing Description Language Is Universal''. [[Conferences#IJCAI2011|IJCAI 2011]] [https://www.ijcai.org/Proceedings/11/Papers/189.pdf pdf]
 
* [[Jean Méhat]], [[Tristan Cazenave]] ('''2011'''). ''A Parallel General Game Player''. [http://www.kuenstliche-intelligenz.de/ KI Journal], Vol. 25, No. 1, [http://www.lamsade.dauphine.fr/~cazenave/papers/rootparallelggp.pdf pdf]
 
* [[Jean Méhat]], [[Tristan Cazenave]] ('''2011'''). ''A Parallel General Game Player''. [http://www.kuenstliche-intelligenz.de/ KI Journal], Vol. 25, No. 1, [http://www.lamsade.dauphine.fr/~cazenave/papers/rootparallelggp.pdf pdf]
 
* [[Mesut Kirci]], [[Nathan Sturtevant]], [[Jonathan Schaeffer]] ('''2011'''). ''A GGP Feature Learning Algorithm''. [http://www.informatik.uni-trier.de/~ley/db/journals/ki/ki25.html#KirciSS11 KI 25(1)]: 35-42, [http://web.cs.du.edu/~sturtevant/papers/FeatureLearning.pdf pdf]
 
* [[Mesut Kirci]], [[Nathan Sturtevant]], [[Jonathan Schaeffer]] ('''2011'''). ''A GGP Feature Learning Algorithm''. [http://www.informatik.uni-trier.de/~ley/db/journals/ki/ki25.html#KirciSS11 KI 25(1)]: 35-42, [http://web.cs.du.edu/~sturtevant/papers/FeatureLearning.pdf pdf]
Line 53: Line 60:
 
* [[Jacek Mańdziuk]], [[Maciej Świechowski]] ('''2012'''). ''Generic Heuristic Approach to General Game Playing''. [http://www.informatik.uni-trier.de/~ley/db/conf/sofsem/sofsem2012.html#MandziukS12 38. SOFSEM], [http://www.mini.pw.edu.pl/~mandziuk/PRACE/SOFSEM12.pdf pdf]
 
* [[Jacek Mańdziuk]], [[Maciej Świechowski]] ('''2012'''). ''Generic Heuristic Approach to General Game Playing''. [http://www.informatik.uni-trier.de/~ley/db/conf/sofsem/sofsem2012.html#MandziukS12 38. SOFSEM], [http://www.mini.pw.edu.pl/~mandziuk/PRACE/SOFSEM12.pdf pdf]
 
'''2013'''
 
'''2013'''
 +
* [[Michael Genesereth]], [[Yngvi Björnsson]] ('''2013'''). ''[https://aaai.org/ojs/index.php/aimagazine/article/view/2475 The International 
General Game Playing Competition].''  [[AAAI#AIMAG|AI Magazine]], Vol. 34, No. 2
 
* [[Yngvi Björnsson]], [[Stephan Schiffel]] ('''2013'''). ''[http://scholar.google.com/citations?view_op=view_citation&hl=en&user=jRcb4G4AAAAJ&citation_for_view=jRcb4G4AAAAJ:7PzlFSSx8tAC Comparison of GDL Reasoners]''. [[Conferences#IJCAI2013|IJCAI 2013]] <ref>[https://en.wikipedia.org/wiki/Game_Description_Language Game Description Language from Wikipedia]</ref>
 
* [[Yngvi Björnsson]], [[Stephan Schiffel]] ('''2013'''). ''[http://scholar.google.com/citations?view_op=view_citation&hl=en&user=jRcb4G4AAAAJ&citation_for_view=jRcb4G4AAAAJ:7PzlFSSx8tAC Comparison of GDL Reasoners]''. [[Conferences#IJCAI2013|IJCAI 2013]] <ref>[https://en.wikipedia.org/wiki/Game_Description_Language Game Description Language from Wikipedia]</ref>
 
* [[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]], [[Alex Graves]], [[Ioannis Antonoglou]], [[Daan Wierstra]], [[Martin Riedmiller]] ('''2013'''). ''Playing Atari with Deep Reinforcement Learning''. [http://arxiv.org/abs/1312.5602 arXiv:1312.5602] <ref>[http://www.nervanasys.com/demystifying-deep-reinforcement-learning/ Demystifying Deep Reinforcement Learning] by [http://www.nervanasys.com/author/tambet/ Tambet Matiisen], [http://www.nervanasys.com/ Nervana], December 21, 2015</ref>
 
* [[Volodymyr Mnih]], [[Koray Kavukcuoglu]], [[David Silver]], [[Alex Graves]], [[Ioannis Antonoglou]], [[Daan Wierstra]], [[Martin Riedmiller]] ('''2013'''). ''Playing Atari with Deep Reinforcement Learning''. [http://arxiv.org/abs/1312.5602 arXiv:1312.5602] <ref>[http://www.nervanasys.com/demystifying-deep-reinforcement-learning/ Demystifying Deep Reinforcement Learning] by [http://www.nervanasys.com/author/tambet/ Tambet Matiisen], [http://www.nervanasys.com/ Nervana], December 21, 2015</ref>
 +
* [[John Levine]], [[Clare Bates Congdon]], [[Marc Ebner]], [[Graham Kendall]], [[Simon Lucas]], [[Risto Miikkulainen]], [[Tom Schaul]], [[Tommy Thompson]] ('''2013'''). ''[https://drops.dagstuhl.de/opus/volltexte/2013/4337/ General Video Game Playing]''. [https://dblp.uni-trier.de/db/conf/dagstuhl/dfu6.html Artificial and Computational Intelligence in Games 2013]
 +
* [[Marc Ebner]], [[John Levine]], [[Simon Lucas]], [[Tom Schaul]], [[Tommy Thompson]], [[Julian Togelius]] ('''2013'''). ''[https://drops.dagstuhl.de/opus/volltexte/2013/4338/ Towards a Video Game Description Language]''. [https://dblp.uni-trier.de/db/conf/dagstuhl/dfu6.html Artificial and Computational Intelligence in Games 2013]
 
'''2014'''
 
'''2014'''
* [[Michael Genesereth]], [[Michael Thielscher]] ('''2014'''). ''[http://www.morganclaypool.com/doi/abs/10.2200/S00564ED1V01Y201311AIM024 General Game Playing]''. [http://www.morganclaypool.com/toc/aim/8/2 Synthesis Lectures on Artificial Intelligence and Machine Learning], [http://www.morganclaypool.com/ Morgan & Claypool Publishers]
+
* [[Michael Genesereth]], [[Michael Thielscher]] ('''2014'''). ''[https://www.morganclaypool.com/doi/abs/10.2200/S00564ED1V01Y201311AIM024 General Game Playing]''. [https://www.morganclaypool.com/toc/aim/1/1 Synthesis Lectures on Artificial Intelligence and Machine Learning], March 2014
 
* [[Stephan Schiffel]], [[Michael Thielscher]] ('''2014'''). ''[https://www.jair.org/papers/paper4115.html Representing and Reasoning About the Rules of General Games With Imperfect Information]''. [https://www.jair.org/vol/vol49.html JAIR Vol. 49]
 
* [[Stephan Schiffel]], [[Michael Thielscher]] ('''2014'''). ''[https://www.jair.org/papers/paper4115.html Representing and Reasoning About the Rules of General Games With Imperfect Information]''. [https://www.jair.org/vol/vol49.html JAIR Vol. 49]
 
* [[Edouard Bonnet|Édouard Bonnet]], [[Abdallah Saffidine]] ('''2014'''). ''On the Complexity of General Game Playing''. [[ECAI CGW 2014]]
 
* [[Edouard Bonnet|Édouard Bonnet]], [[Abdallah Saffidine]] ('''2014'''). ''On the Complexity of General Game Playing''. [[ECAI CGW 2014]]
Line 64: Line 74:
 
* [[Maciej Świechowski]], [[Jacek Mańdziuk]] ('''2014'''). ''Self-Adaptation of Playing Strategies in General Game Playing''.  [[IEEE#TOCIAIGAMES|IEEE Transactions on Computational Intelligence and AI in Games]], Vol. 6, No. 4
 
* [[Maciej Świechowski]], [[Jacek Mańdziuk]] ('''2014'''). ''Self-Adaptation of Playing Strategies in General Game Playing''.  [[IEEE#TOCIAIGAMES|IEEE Transactions on Computational Intelligence and AI in Games]], Vol. 6, No. 4
 
==2015 ...==
 
==2015 ...==
 +
* [[Alexander Braylan]], [[Mark Hollenbeck]], [[Elliot Meyerson]], [[Risto Miikkulainen]] ('''2015'''). ''Reuse of Neural Modules for General Video Game Playing''. [https://arxiv.org/abs/1512.01537 arXiv:1512.01537]
 
* [[Cameron Browne]] ('''2016'''). ''A Class Grammar for General Games''. [[CG 2016]]
 
* [[Cameron Browne]] ('''2016'''). ''A Class Grammar for General Games''. [[CG 2016]]
 
* [[Nera Nesic]], [[Stephan Schiffel]] ('''2016'''). ''Heuristic Function Evaluation Framework''. [[CG 2016]]
 
* [[Nera Nesic]], [[Stephan Schiffel]] ('''2016'''). ''Heuristic Function Evaluation Framework''. [[CG 2016]]
 
* [[Maciej Świechowski]], [[Jacek Mańdziuk]] ('''2016'''). ''A Hybrid Approach to Parallelization of Monte Carlo Tree Search in General Game Playing''. [https://www.springer.com/de/book/9783319301648 Challenging Problems and Solutions in Intelligent Systems], [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]
 
* [[Maciej Świechowski]], [[Jacek Mańdziuk]] ('''2016'''). ''A Hybrid Approach to Parallelization of Monte Carlo Tree Search in General Game Playing''. [https://www.springer.com/de/book/9783319301648 Challenging Problems and Solutions in Intelligent Systems], [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]
* [[Hui Wang]], [[Michael Emmerich]], [[Aske Plaat]] ('''2018'''). ''Monte Carlo Q-learning for General Game Playing''. [https://arxiv.org/abs/1802.05944 arXiv:1802.05944] » [[Monte-Carlo Tree Search]], [[Reinforcement Learning]]
+
* [[Tristan Cazenave]], [[Abdallah Saffidine]], [[Michael Schofield]], [[Michael Thielscher]] ('''2016'''). ''Nested Monte Carlo Search for Two-Player Games''. [[Conferences#AAAI-2016|AAAI 2016]], [https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12134/11652 pdf]
 +
* [[Michael Thielscher]] ('''2017'''). ''GDL-III: A Description Language for Epistemic General Game Playing''. [[Conferences#IJCAI2017|IJCAI 2017]], [https://www.ijcai.org/proceedings/2017/0177.pdf pdf]
 +
* [[Hui Wang]], [[Michael Emmerich]], [[Aske Plaat]] ('''2018'''). ''Monte Carlo Q-learning for General Game Playing''. [https://arxiv.org/abs/1802.05944 arXiv:1802.05944] » [[Monte-Carlo Tree Search|MCTS]], [[Reinforcement Learning]]
 +
* [[Hui Wang]], [[Michael Emmerich]], [[Aske Plaat]] ('''2018'''). ''Assessing the Potential of Classical Q-learning in General Game Playing''. [https://arxiv.org/abs/1810.06078 arXiv:1810.06078]
 +
* [[Armin Chitizadeh]], [[Michael Thielscher]] ('''2018'''). ''[https://link.springer.com/chapter/10.1007/978-3-030-24337-1_5 Iterative Tree Search in General Game Playing with Incomplete Information]''. [[Conferences#CGW|CGW 2018]] @ [[Conferences#IJCAI2018|IJCAI 2018]]
 +
* [[Armin Chitizadeh]], [[Michael Thielscher]] ('''2018'''). ''[https://link.springer.com/chapter/10.1007/978-3-030-03991-2_5 General Language Evolution in General Game Playing]''. [https://dblp.uni-trier.de/db/conf/ausai/ausai2018.html Australasian Conference on Artificial Intelligence 2018]
 +
==2020 ...==
 +
* [https://scholar.google.co.uk/citations?user=tC5klQYAAAAJ&hl=en Raluca D. Gaina], [https://dblp.uni-trier.de/pers/hd/d/Devlin:Sam Sam Devlin], [[Simon Lucas]], [[Diego Perez|Diego Perez-Liebana]] ('''2020'''). ''Rolling Horizon Evolutionary Algorithms for General Video Game Playing''. [https://arxiv.org/abs/2003.12331 arXiv:2003.12331]
 +
* [https://dblp.uni-trier.de/pers/hd/b/Balla:Martin Martin Balla], [[Simon Lucas]], [[Diego Perez|Diego Perez-Liebana]] ('''2020'''). ''Evaluating Generalisation in General Video Game Playing''. [https://arxiv.org/abs/2005.11247 arXiv:2005.11247]
  
 
=External Links=  
 
=External Links=  
Line 73: Line 92:
 
* [https://en.wikipedia.org/wiki/General_Game_Playing General Game Playing from Wikipedia]
 
* [https://en.wikipedia.org/wiki/General_Game_Playing General Game Playing from Wikipedia]
 
* [https://en.wikipedia.org/wiki/General_video_game_playing General video game playing from Wikipedia]
 
* [https://en.wikipedia.org/wiki/General_video_game_playing General video game playing from Wikipedia]
* [http://games.stanford.edu/ General Game Playing] from [[Stanford University|Stanford]]
+
* [http://ggp.stanford.edu/ General Game Playing] from [[Stanford University|Stanford]]
 
==GDL==
 
==GDL==
 
* <span id="GDL"></span>[https://en.wikipedia.org/wiki/Game_Description_Language Game Description Language from Wikipedia]
 
* <span id="GDL"></span>[https://en.wikipedia.org/wiki/Game_Description_Language Game Description Language from Wikipedia]
Line 85: Line 104:
 
=References=  
 
=References=  
 
<references />
 
<references />
 
 
'''[[Games|Up one Level]]'''
 
'''[[Games|Up one Level]]'''

Latest revision as of 13:11, 17 July 2020

Home * Games * General Game Playing

General Game Playing, (GGP)
an approach of Artificial Intelligence programs to be able to play more than one game successfully. For games like chess, computers are programmed to play these games using a specially designed algorithm - a chess playing program cannot play checkers. A General Game Playing system, if well designed, would be able to help in other areas, such as in providing intelligence for search and rescue missions [1]. One well know commercial General Game program is Zillions of Games by Jeff Mallett and Mark Lefler [2] .

GVGP

General video game playing (GVGP) is the concept of GGP adjusted to the purpose of playing video games [3], and to apply reinforcement learning and Monte-Carlo tree search to master video and Atari games of skill and strategy.

Selected Publications

1968 ...

1970 ...

1990 ...

2000 ...

2005 ...

2010 ...

2011

2012

2013

2014

2015 ...

2020 ...

External Links

General Game Playing

GDL

Player

References

Up one Level