Algemene speletjie speel (KI)

Algemene speletjie speel (ASS) is die ontwerp van kunsmatige intelligensie-programme om meer as een speletjie suksesvol te kan speel.[1][2][3] Vir baie speletjies soos skaak, is rekenaars geprogrammeer om hierdie speletjies te speel deur 'n spesiaal ontwerpte algoritme te gebruik, wat nie na 'n ander konteks oorgedra kan word nie. Byvoorbeeld, 'n rekenaarprogram wat skaak speel kan nie dambord speel nie. Algemene spel word beskou as 'n noodsaaklike mylpaal op pad na kunsmatige algemene intelligensie.[4]

Deel van 'n reeks oor
Kunsmatige intelligensie

Algemene videospeletjie speel (AVSS) is die konsep van ASS wat aangepas is vir die doel van die speel van videospeletjies. Vir videospeletjies moet spelreëls óf oor veelvuldige weergawes deur kunsmatige spelers soos TD-Gammon aangeleer word,[5] óf word vooraf met die hand in 'n domeinspesifieke taal gedefinieer en vooraf aan kunsmatige spelers gestuur word[6][7] soos in tradisionele AAS. Vanaf 2013 is aansienlike vordering gemaak na aanleiding van die diepversterkingsleerbenadering, insluitend die ontwikkeling van programme wat kan leer om Atari 2600-speletjies te speel[8][5][9][10][11]sowel as 'n program wat kan leer om Nintendo Entertainment System-speletjies te speel.[12][13][14]

Die eerste kommersiële gebruik van algemene speltegnologie was Zillions of Games in 1998. Algemene spelspel is ook voorgestel vir handelsagente in voorsieningskettingbestuur daaronder prysonderhandeling in aanlynveilings vanaf 2003.[15][16][17][18]

Verwysings
  1. Pell, Barney (1992). H. van den Herik; L. Allis (reds.). "Metagame: a new challenge for games and learning" [Heuristic programming in artificial intelligence 3–the third computerolympiad] (PDF). Ellis-Horwood. Geargiveer (PDF) vanaf die oorspronklike op 17 Februarie 2020. Besoek op 17 Februarie 2020. {{cite journal}}: Cite journal requires |journal= (hulp)
  2. Pell, Barney (1996). "A Strategic Metagame Player for General Chess-Like Games". Computational Intelligence (in Engels). 12 (1): 177–198. doi:10.1111/j.1467-8640.1996.tb00258.x. ISSN 1467-8640. S2CID 996006.
  3. Genesereth, Michael; Love, Nathaniel; Pell, Barney (15 Junie 2005). "General Game Playing: Overview of the AAAI Competition". AI Magazine (in Engels). 26 (2): 62. doi:10.1609/aimag.v26i2.1813. ISSN 2371-9621.
  4. Canaan, Rodrigo; Salge, Christoph; Togelius, Julian; Nealen, Andy (2019). Proceedings of the 14th International Conference on the Foundations of Digital Games [Proceedings of the 14th International Conference on the Leveling the playing field: fairness in AI versus human game benchmarks]. pp. 1–8. doi:10.1145/3337722. ISBN 9781450372176. S2CID 58599284. {{cite book}}: |website= ignored (hulp)
  5. Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Graves, Alex; Antonoglou, Ioannis; Wierstra, Daan; Riedmiller, Martin (2013). "Playing Atari with Deep Reinforcement Learning" (PDF). Conference on Neural Information Processing Systems. Geargiveer (PDF) vanaf die oorspronklike op 12 September 2014. Besoek op 25 April 2015.
  6. Schaul, Tom (Augustus 2013). "A video game description language for model-based or interactive learning". 2013 IEEE Conference on Computational Inteligence in Games (CIG). pp. 1–8. CiteSeerX 10.1.1.360.2263. doi:10.1109/CIG.2013.6633610. ISBN 978-1-4673-5311-3. S2CID 812565.
  7. Levine, John; Congdon, Clare Bates; Ebner, Marc; Kendall, Graham; Lucas, Simon M.; Miikkulainen, Risto; Schaul, Tom; Thompson, Tommy (2013). "General Video Game Playing". Artificial and Computational Intelligence in Games. Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik. 6: 77–83. Geargiveer vanaf die oorspronklike op 9 April 2016. Besoek op 25 April 2015.
  8. Bowling, M.; Veness, J.; Naddaf, Y.; Bellemare, M. G. (14 Junie 2013). "The Arcade Learning Environment: An Evaluation Platform for General Agents". Journal of Artificial Intelligence Research (in Engels). 47: 253–279. arXiv:1207.4708. doi:10.1613/jair.3912. ISSN 1076-9757. S2CID 1552061.
  9. Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A.; Veness, Joel; Hassabis, Demis; Bellemare, Marc G.; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K.; Stig Petersen, Georg Ostrovski; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane (26 Februarie 2015). "Human-level control through deep reinforcement learning". Nature. 518 (7540): 529–533. Bibcode:2015Natur.518..529M. doi:10.1038/nature14236. PMID 25719670. S2CID 205242740.
  10. Korjus, Kristjan; Kuzovkin, Ilya; Tampuu, Ardi; Pungas, Taivo (2014). "Replicating the Paper "Playing Atari with Deep Reinforcement Learning"" (PDF). University of Tartu. Geargiveer (PDF) vanaf die oorspronklike op 18 Desember 2014. Besoek op 25 April 2015.
  11. Guo, Xiaoxiao; Singh, Satinder; Lee, Honglak; Lewis, Richard L.; Wang, Xiaoshi (2014). "Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning" (PDF). NIPS Proceedingsβ. Conference on Neural Information Processing Systems. Geargiveer (PDF) vanaf die oorspronklike op 17 November 2015. Besoek op 25 April 2015.
  12. Murphy, Tom (2013). "The First Level of Super Mario Bros. is Easy with Lexicographic Orderings and Time Travel ... after that it gets a little tricky." (PDF). SIGBOVIK. Geargiveer (PDF) vanaf die oorspronklike op 26 April 2013. Besoek op 25 April 2015.
  13. Murphy, Tom. "learnfun & playfun: A general technique for automating NES games". Geargiveer vanaf die oorspronklike op 19 April 2015. Besoek op 25 April 2015.
  14. Teller, Swizec (28 Oktober 2013). "Week 2: Level 1 of Super Mario Bros. is easy with lexicographic orderings and". A geek with a hat. Geargiveer vanaf die oorspronklike op 30 April 2015. Besoek op 25 April 2015.
  15. McMillen, Colin (2003). "Toward the Development of an Intelligent Agent for the Supply Chain Management Game of the 2003 Trading Agent Competition" [2003 Trading Agent Competition]. Master's Thesis. Minneapolis, MN: University of Minnesota. S2CID 167336006. {{cite journal}}: Cite journal requires |journal= (hulp)
  16. Zhang, Dongmo (2009). From general game descriptions to a market specification language for general trading agents [Agent-mediated electronic commerce. Designing trading strategies and mechanisms for electronic markets.]. Berlin, Heidelberg: Springer. pp. 259–274. Bibcode:2010aecd.book..259T. CiteSeerX 10.1.1.467.4629.
  17. "AGAPE - An Auction LanGuage for GenerAl Auction PlayErs". AGAPE (in Frans). 8 Maart 2019. Geargiveer vanaf die oorspronklike op 2 Augustus 2021. Besoek op 5 Maart 2020.
  18. Michael, Friedrich; Ignatov, Dmitry (2019). "General Game Playing B-to-B Price Negotiations" (PDF). CEUR Workshop Proceedings. -2479: 89–99. Geargiveer (PDF) vanaf die oorspronklike op 6 Desember 2019. Besoek op 5 Maart 2020.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.