Game artificial intelligence based using reinforcement learning

Procedia Engineering

Volumn 50, Issue , 2012, Pages 555-565

  Agung, Albertus ^a   Gaol, Ford Lumban ^a  

^a BINA NUSANTARA UNIVERSITY   (Indonesia)

Author keywords

Artificial intelligence; Game; Q learning; Reinforcement learning; Sarsa

Indexed keywords

EID: 84891758993     PISSN: 18777058     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1016/j.proeng.2012.10.060     Document Type: Conference Paper

References (8)

1. Aha DW, Molineaux M and Ponsen M. Learning to Win: Case-Based Plan Selection in a Real-Time Strategy Game, In Proceedings of International Conference onCase-Based Reasoning, Chicago, USA, 23-26 August 2005, pp. 5-20.
2. Fang YP, Ting IH. Applying Reinforcement Learning for the AI in a Tank-Battle Game. JOURNAL OF SOFTWARE, VOL. 5, NO. 12, DECEMBER 2010.
3. Sutton RS, Barto AG. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA, 1998.
4. Eden T, Knittel A, Uffelen RV. Introduction to Reinforcement Learning. http://www.cse.unsw.edu.au/~cs9417ml/RL1/index.html.
5. Kok E. Adaptive reinforcement learning agents in RTS games. Intelligent System group, University Utrecht, TheNetherlands; 2008.
6. Fang, Y.-P., & Ting, I.-H. (2010). Applying Reinforcement Learning for the AI in a Tank-Battle Game. Journal of lSoftware, Vol. 5, No. 12, December 2010.
7. Mici, A., Arnarsson, D., & Jónsson, V. (2011). Developing Game AI For The Real-Time Strategy Game Starcraft. Research Report Spring 2011, Reykjavik University.
8. Takadama, K. & Fujita, H. Lessons learned from comparison between Q-learning and Sarsa Agents in Bargaining Game. NAACSOS (North American Association for Computational Social and Organizational Science) Conference 2004.