Learning companion behaviors using reinforcement learning in games
作者： Duane Szafron , Richard Zhao , AmirAli Sharifi
DOI:
关键词:
摘要: Our goal is to enable Non Player Characters (NPC) in computer games exhibit natural behaviors. The quality of behaviors affects the game experience especially story-based games, which rely on player-NPC interactions. We used Reinforcement Learning NPC companions develop preferences for actions. implemented our RL technique BioWare Corp.'s Neverwinter Nights. experiments evaluate an companion's regarding traps. method enables NPCs rapidly learn reasonable and adapt changes game.
elsevier.com
ualberta.ca 参考文章(10)
Maria Cutumisu, Richard S. Sutton, Duane Szafron, Michael Bowling, Agent learning using action-dependent learning rates in computer role-playing games national conference on artificial intelligence. pp. 22- 29 ,(2008)
Pieter Spronck, Timor Timuri, Jaap van den Herik, Automatic rule ordering for dynamic scripting national conference on artificial intelligence. pp. 49- 54 ,(2007)
Stephen Lee-Urban, Héctor Muñoz-Avila, Megan Smith, RETALIATE: learning winning policies in first-person shooter games innovative applications of artificial intelligence. pp. 1801- 1806 ,(2007)
Damien Ernst, Arthur Louette, Introduction to Reinforcement Learning MIT Press. ,(1998)
Kathryn E Merrick, Mary Lou Maher, None, Motivated Reinforcement Learning: Curious Characters for Multiuser Games ,(2009)
Pieter Spronck, Marc Ponsen, Ida Sprinkhuizen-Kuyper, Eric Postma, Adaptive game AI with dynamic scripting Machine Learning. ,vol. 63, pp. 217- 248 ,(2006) , 10.1007/S10994-006-6205-6
A.G. Barto, R.S. Sutton, Reinforcement Learning: An Introduction ,(1988)
Michael Holmes, Charles Isbell, Ashwin Ram, Juan Santamaria, Arya Irani, Manu Sharma, Transfer learning in real-time strategy games using hybrid CBR/RL international joint conference on artificial intelligence. pp. 1041- 1046 ,(2007)
Kathryn Merrick, Mary Lou Maher, Motivated Reinforcement Learning TAEBC-2009. ,(2009) , 10.1007/978-3-540-89187-1
C. J. C. H. Watkins, Learning from delayed rewards Ph. D thesis, Cambridge University Psychology Department. ,(1989)