Abstract
Artificial intelligence for digital games constitutes the implementation of a set of algorithms and techniques from both traditional and modern artificial intelligence in order to provide solutions to a range of game dependent problems. However, the majority of current approaches lead to predefined, static and predictable game agent responses, with no ability to adjust during game-play to the behaviour or playing style of the player. Machine learning techniques provide a way to improve the behavioural dynamics of computer controlled game agents by facilitating the automated generation and selection of behaviours, thus enhancing the capabilities of digital game artificial intelligence and providing the opportunity to create more engaging and entertaining game-play experiences. This paper provides a survey of the current state of academic machine learning research for digital game environments, with respect to the use of techniques from neural networks, evolutionary computation and reinforcement learning for game agent control.
Similar content being viewed by others
References
Agapitos A, Togelius J, Lucas SM (2007a) Evolving controllers for simulated car racing using object orientated genetic programming. In: Thierens D et al (eds) Proceedings of the 2007 genetic and evolutionary computation conference. ACM Press, pp 1543–1550
Agapitos A, Togelius J, Lucas SM (2007b) Multiobjective techniques for the use of state in genetic programming applied to simulated car racing. In: Proceedings of the 2007 IEEE congress on evolutionary computation. IEEE Press, pp 1562–1569
Baekkelund C (2006) A brief comparison of machine learning methods. In: Rabin S (eds) AI game programming wisdom 3, 1st edn. Charles River Media, Hingham
Baluja S (1994) Population-based incremental learning: a method for integrating genetic search based function optimization and competitive learning. Technical report CMU-CS-94-163, Carnegie Mellon University
Bauckhage C, Thurau C (2004) Towards a fair ‘n square aimbot—using mixtures of experts to learn context aware weapon handling. In: El-Rhalibi A, Van Welden D (eds) Proceedings of the 5th international conference on intelligent games and simulation. Eurosis, pp 20–24
Beyer H-G (2001) The theory of evolutionary strategies. Springer, Berlin
Billings D, Davidson A, Schaeffer J, Szafron D (2002) The challenge of poker. Artif Intell 134(1–2): 201–240
Blumberg B, Downie M, Ivanov Y, Berlin M, Johnson MP, Tomlinson B (2002) Integrated learning for interactive synthetic characters. In: Proceedings of the 29th annual conference on computer graphics and interactive techniques. ACM Press, pp 417–426
Bradley J, Hayes G (2005a) Adapting reinforcement learning for computer games: using group utility functions. In: Kendall G, Lucas SM (eds) Proceedings of the 2005 IEEE symposium on computational intelligence and games. IEEE Press, Piscataway
Bradley J, Hayes G (2005b) Group utility functions: learning equilibria between groups of agents in computer games by modifying the reinforcement signal. In: Proceedings of the 2005 IEEE congress on evolutionary computation. IEEE Press, pp 1914–1921
Breiman L (1996) Bagging predictors. Mach Learn 24(2): 123–140
Bryant BD, Miikkulainen R (2003) Neuroevolution for adaptive teams. In: Proceedings of the 2003 IEEE congress on evolutionary computation. IEEE Press, pp 2194–2201
Bryant BD, Miikkulainen R (2006a) Exploiting sensor symmetries in example-based training for intelligent agents. In: Louis SJ, Kendall G (eds) Proceedings of the 2006 IEEE symposium on computational intelligence and games. IEEE Press, pp 90–97
Bryant BD, Miikkulainen R (2006b) Evolving stochastic controller networks for intelligent game agents. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 1007–1014
Bryant BD, Miikkulainen R (2007) Acquiring visibly intelligent behavior with example-guided neuroevolution. In: Proceedings of the 22nd National conference on artificial intelligence. AAAI Press, Menlo park, pp 801–808
Buckland M (2005) Programming game AI by example. Wordware Publishing, Plano
Buro M (1997) The othello match of the year: Takeshi Murakami vs. Logistello. ICCA J 20(3): 189–193
Campbell M, Hoane AJ, Hsu F-H (2002) Deep blue. Artif Intell 134(1–2): 57–83
Chaperot B, Fyfe C (2006) Improving artificial intelligence in a motocross game. In: Louis SJ, Kendall G (eds) Proceedings of the 2006 IEEE symposium on computational intelligence and games. IEEE Press, pp 181–186
Charles D (2003) Enhancing gameplay: challenges for artificial intelligence in digital games. In: Proceedings of digital games research conference 2003. University of Utrecht, 4–6 November 2003
Charles D, McGlinchey S (2004) The past, present and future of artificial neural networks in digital games. In: Mehdi Q, Gough N, Natkin S, Al-Dabass D (eds) Proceedings of the 5th international conference on computer games: artificial intelligence, design and education. The University of Wolverhampton, pp 163–169
Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6(2): 182–197
DeBoer P-T, Kroese DP, Mannor S, Rubinstein RY (2004) A tutorial on the cross-entropy method. Ann Oper Res 134(1): 19–67
DeJong KA, Sarma J (1992) Generation gaps revisited. In: Whitley D (eds) Foundations of genetic algorithms 2. Morgan Kaufmann, San Mateo, pp 19–28
Demasi P, Cruz AJ (2003) Online coevolution for action games. Int J Intell Games Simul 2: 80–88
Dietterich TG (2000) An overview of MAXQ hierarchical reinforcement learning. In: Choueiry BY, Walsh T (eds) Lecture notes in computer science, vol. 1864. Springer, Berlin, pp 26–44
D’Silva T, Janik R, Chrien M, Stanley KO, Miikkulainen R (2005) Retaining learned behavior during real-time neuroevolution. In: Young M, Laird J (eds) Proceedings of the 1st artificial intelligence and interactive digital entertainment conference. AAAI Press, Menlo Park, pp 39–44
Duan J, Gough NE, Mehdi QH (2002) Multi-agent reinforcement learning for computer game agents. In: Mehdi QH, Gough NE (eds) Proceedings of the 3rd international conference on intelligent games and simulation. The University of Wolverhampton, pp 104–109
Elman JL (1990) Finding structure in time. Cog Sci 14: 179–211
Evans R (2001) The future of AI in games: a personal view. Game Dev 8: 46–49
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Saitta L (ed) Proceedings of the 13th international conference on machine learning. Morgan Kaufmann, pp 148–156
Fürnkranz J (2001) Machine learning in games: a survey. In: Fürnkranz J, Kubat M (eds) Machines that learn to play games. Nova Science Publishers, Huntington, pp 11–59
Gallagher M, Ledwich M (2007) Evolving Pac-Man players: can we learn from raw input? In: Proceedings of the 2007 IEEE symposium on computational intelligence in games. IEEE Press, pp 282–287
Gallagher M, Ryan A (2003) Learning to play Pac-Man: an evolutionary, rule-based approach. In: Proceedings of the 2003 IEEE congress on evolutionary computation. IEEE Press, pp 2462–2469
Galway L, Charles D, Black M (2007) Temporal difference control within a dynamic environment. In: Roccetti M (ed) Proceedings of the 8th international conference on intelligent games and simulation. Eurosis, pp 42–47
Geisler B (2004) Integrated machine learning for behavior modeling in video games. In: Fu D, Henke S, Orkin J (eds) Challenges in game artificial intelligence: papers from the 2004 AAAI workshop. AAAI Press, Menlo Park, pp 54–62
Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, Reading
Gomez F, Miikkulainen R (1997) Incremental evolution of complex general behavior. Adapt Behav 5: 317–342
Gorniak P, Davis I (2007) SquadSmart hierarchical planning and coordinated plan execution for squads of characters. In: Schaeffer J, Mateas M (eds) Proceedings of the 3rd artificial intelligence and interactive digital entertainment conference. AAAI Press, Menlo Park, pp 14–19
Graepel T, Herbrich R, Gold J (2004) Learning to fight. In: Mehdi Q, Gough N, Natkin, S, Al-Dabass D (eds) Proceedings of 5th international conference on computer games: artificial intelligence, design and education. The University of Wolverhampton, pp 193–200
Grand S, Cliff D, Malhotra A (1997) Creatures: artificial life autonomous software agents for home entertainment. In: Proceedings of the 1st international conference on autonomous agents. ACM Press, pp 22–29
Hagan MT, Menhaj M (1994) Training feed-forward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5(6): 989–993
Haykin S (1994) Neural networks: a comprehensive foundation. Prentice-Hall, Upper Saddle River
Hoang H, Lee-Urban S, Muñoz-Avila H (2005) Hierarchical plan representations for encoding strategic game AI. In: Young M, Laird J (eds) Proceedings of the 1st artificial intelligence and interactive digital entertainment conference. AAAI Press, Menlo Park, pp 63–68
Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control and artificial intelligence. MIT Press, Cambridge
Hsu F-H (2002) Behind deep blue: building the computer that defeated the World Chess Champion. Princeton University Press, Princeton
Jacobs R, Jordan M, Nowlan S, Hinton G (1991) Adaptive mixture of local experts. Neural Comput 3(1): 79–87
Kirby N (2004) Getting around the limits of machine learning. In: Rabin S(eds) AI game programming wisdom 2, 1st edn. Charles River Media, Hingham
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43: 59–69
Koza JP (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge
Laird JE, Van Lent M (1999) Developing an artificial intelligence engine. In: Proceedings of the 1999 game developers conference, pp 577–588
Laird JE, Van Lent M (2001) Human level AI’s killer application: interactive computer games. AI Mag 22: 15–25
Louis SJ, McDonnell J (2004) Learning with case-injected genetic algorithms. IEEE Trans Evol Comput 8: 316–327
Louis SJ, Miles C (2005) Playing to learn: case-injected genetic algorithms for learning to play computer games. IEEE Trans Evol Comput 9: 669–681
Lucas SM (2004) Cellz: A simple dynamic game for testing evolutionary algorithms. In: Proceedings of the 2004 IEEE congress on evolutionary computation. IEEE Press, pp 1007–1014
Lucas SM (2005) Evolving a neural network location evaluator to play Ms. Pac-Man. In: Kendall G, Lucas SM (eds) Proceedings of the 2005 IEEE symposium on computational intelligence and games. IEEE Press, pp 203–210
Lucas SM, Kendall G (2006) Evolutionary computation and games. IEEE Comput Intell Mag. February, pp 10–18
Lucas SM, Togelius J (2007) Point-to-point car racing: an initial study of evolution versus temporal difference learning. In: Proceedings of the 2007 IEEE symposium on computational intelligence and games. IEEE Press, pp 260–267
MacNamee B, Cunningham P (2001) Proposal for an agent architecture for proactive persistent non player characters. In: Proceedings of the 12th Irish conference on artificial intelligence and cognitive science, pp 221–232
MacNamee B, Cunningham P (2003) Creating socially interactive non player characters: the μ-SIC system. Int J Intell Games Simul 2: 28–35
Maderia C, Corruble V, Ramalho G, Ratitch B (2004) Bootstrapping the learning process for semi-automated design of a challenging game AI. In: Fu D, Henke S, Orkin J (eds) Challenges in game artificial intelligence: papers from the 2004 AAAI workshop. AAAI Press, Menlo Park, pp 72–76
Maderia C, Corruble V, Ramalho G (2006) Designing a reinforcement learning-based adaptive AI for large-scale strategy games. In: Laird J, Schaeffer J (eds) Proceedings of the 2nd artificial intelligence and interactive digital entertainment conference. AAAI Press, Menlo Park, pp 121–123
Maes P (1995) Artificial life meets entertainment: lifelike autonomous agents. Commun ACM 38: 108–114
Manslow J (2002) Learning and adaptation. In: Rabin S (eds) AI game programming wisdom, 1st edn. Charles River Media, Hingham
McGlinchey S (2003) Learning of AI players from game observation data. In: Mehdi Q, Gough N, Natkin S (eds) Proceedings of the 4th international conference on intelligent games and simulation. Eurosis, pp 106–110
Miconi T, Channon A (2006) The N-strikes-out algorithm: a steady-state algorithm for coevolution. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 1639–1646
Miikkulainen R, Bryant BD, Cornelius R, Karpov IV, Stanley KO, Yong CH (2006) Computational intelligence in games. In: Yen GY, Fogel DB (eds) Computational intelligence: principles and practice. IEEE Computational Intelligence Society, Piscataway, pp 155–191
Miles C, Louis SJ (2006) Towards the co-evolution of influence map tree based strategy game players. In: Louis SJ, Kendall G (eds) Proceedings of the 2006 IEEE symposium on computational intelligence and games. IEEE Press, pp 75–82
Miles C, Louis SJ, Cole N, McDonnell J (2004a) Learning to play like a human: case injected genetic algorithms for strategic computer gaming. In: Proceedings of the 2004 IEEE congress on evolutionary computing. IEEE Press, pp 1441–1448
Miles C, Louis SJ, Drewes R (2004b) Trap avoidance in strategic computer game playing with case injected genetic algorithms. In: Proceedings of the 2004 genetic and evolutionary computation conference. ACM Press, pp 1365–1376
Miles C, Quiroz J, Leigh R, Louis SJ (2007) Co-evolving influence map tree based strategy game players. In: Proceedings of the 2007 IEEE symposium on computational intelligence and games. IEEE Press, pp 88–95
Orkin J (2005) Agent architecture considerations for real-time planning in games. In: Young M, Laird J (eds) Proceedings of the 1st artificial intelligence and interactive digital entertainment conference. AAAI Press, Menlo Park, pp 105–110
Parker G, Rawlins G (1996) Cyclic genetic algorithms for the locomotion of hexapod robots. In: Proceedings of the 2nd world automation congress, pp 617–622
Parker GB, Doherty TS, Parker M (2005a) Evolution and prioritization of survival strategies for a simulated robot in xpilot. In: Proceedings of the 2005 IEEE congress on evolutionary computing. IEEE Press, pp 2410–2415
Parker G, Parker M, Johnson S (2005b) Evolving autonomous agent control in the xpilot environment. In: Proceedings of the 2005 IEEE congress on evolutionary computation. IEEE Press, pp 2416–2421
Parker GB, Doherty TS, Parker M (2006) Generation of unconstrained looping programs for control of xpilot agents. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 1216–1223
Parker M, Parker GB (2006a) Learning control for xpilot agents in the core. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 800–807
Parker GB, Parker M (2006b) The incremental evolution of attack agents in xpilot. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 969–975
Parker M, Parker GB (2006c) Using a queue genetic algorithm to evolve xpilot control strategies on a distributed system. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 1202–1207
Parker M, Parker GB (2007a) The Evolution of multi-layer neural networks for the control of xpilot agents. In: Proceedings of the 2007 IEEE symposium on computational intelligence and games. IEEE Press, pp 232–237
Parker GB, Parker M (2007b) Evolving parameters for xpilot combat agents. In: Proceedings of the 2007 IEEE symposium on computational intelligence and games. IEEE Press, pp 238–243
Pfeiffer M (2004) Reinforcement learning of strategies for settlers of catan. In: Mehdi Q, Gough N, Natkin, S, Al-Dabass D (eds) Proceedings of the 5th international conference on computer games: artificial intelligence, design and education. The University of Wolverhampton, pp 384–388
Ponsen M, Spronck P (2004) Improving adaptive game AI with evolutionary learning. In: Mehdi Q, Gough N, Natkin, S, Al-Dabass D (eds) Proceedings of the 5th international conference on computer games: artificial intelligence, design and education. The University of Wolverhampton, pp 389–396
Ponsen M, Spronck P, Tuyls K (2006) Hierarchical reinforcement learning with deictic representation in a computer game. In: Schobbens P-Y, Vanhoof W, Schwanen G (eds) Proceedings of the 18th Belgium-Netherlands conference on artificial intelligence. University of Namur, pp 251–258
Pottinger D (2000) The Future of AI in games. Game Dev 8: 36–39
Rumelhart DE, Hinton GE, Williams RJ (1989) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. MIT Press, Cambridge
Rummery GA, Niranjan M (1994) On-line Q-learning using connectionist systems. Technical Report CUED/F-INFENG/TR 166, Cambridge University, UK
Samuel AL (1959) Some studies in machine learning using the game of checkers. IBM J Res Dev 3(3): 211–229
Samuel AL (1967) Some studies in machine learning using the game of checkers. ii – recent progress. IBM J Res Dev 11(6): 601–617
Schaeffer J (1997) One jump ahead: challenging human supremacy in checkers. Springer, Berlin
Schaeffer J (2000) The games computers (and people) play. In: Zelkowitz M (eds) Advances in computers: 50. Academic Press, San Diego, pp 189–266
Schaeffer J, Vanden Herik HJ (2002) Games, computers, and artificial intelligence. Artif Intell 134: 1–7
Schwab B (2004) AI game engine programming, 1st edn. Charles River Media, Hingham
Spronck P, Sprinkhuizen-Kuyper I, Postma E (2003a) Improving opponent intelligence through offline evolutionary learning. Int J Intell Games Sim 2: 20–27
Spronck P, Sprinkhuizen-Kuyper I, Postma E (2003b) Online adaptation of game opponent AI in simulation and in practice. In: Mehdi Q, Gough N, Natkin S (eds) Proceedings of the 4th international conference on intelligent games and simulation. Eurosis, pp 93–100
Spronck P, Ponsen M, Sprinkhuizen-Kuyper I, Postma E (2006) Adaptive game AI with dynamic scripting. Mach Learn 63: 217–248
Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10: 99–127
Stanley KO, Bryant BD, Miikkulainen R (2005a) Real-time neuroevolution in the NERO video game. IEEE Trans Evol Comput 9: 653–668
Stanley KO, Bryant BD, Miikkulainen R (2005b) Evolving neural network agents in the NERO video game. In: Kendall G, Lucas SM (eds) Proceedings of the 2005 IEEE symposium on computational intelligence and games. IEEE Press, Piscataway, NJ
Sutton RS (1988) Learning to predict by the method of temporal differences. Mach Learn 3: 9–44
Sutton RS (1996) Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Touretzky DS, Mozer MC, Hasselmo ME (eds) Advances in neural information processing systems 8. MIT Press, Cambridge, pp 1038–1044
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge
Szita I, Lõrincz A (2006) Learning tetris using noisy cross-entropy method. Neural Comput 18: 2936–2941
Szita I, Lõrincz A (2007) Learning to play using low-complexity rule-based policies: illustrations through Ms. Pac-Man. J Artif Intell Res 30: 659–684
Tesauro G (1995) Temporal difference learning and td-gammon. Commun ACM 38(3): 58–68
Thurau C, Bauckhage C, Sagerer G (2003) Combining self-organizing maps and multilayer perceptrons to learn bot-behavior for a commercial game. In: Mehdi Q, Gough N, Natkin S (eds) Proceedings of the 4th international conference on intelligent games and simulation. Eurosis, pp 119–123
Togelius J, Lucas SM (2005) Evolving controllers for simulated car racing. In: Proceedings of the 2005 IEEE congress on evolutionary computation. IEEE Press, pp 1906–1913
Togelius J, Lucas SM (2006) Evolving robust and specialized car racing skills. In: Proceedings of the 2006 IEEE congress on evolutionary computation. IEEE Press, pp 1187–1194
Togelius J, Burrow P, Lucas SM (2007a) Multi-population competitive co-evolutions of car racing controllers. In: Proceedings of the 2007 IEEE congress on evolutionary computation. IEEE Press, pp 4043–4050
Togelius J, Nardi RD, Lucas SM (2007b) Towards automatic personalized content creation for racing games. In: Proceedings of the 2007 IEEE symposium on computational intelligence and games. IEEE Press, pp 252–259
Tozour P (2001) Influence mapping. In: DeLoura M (eds) Game programming gems, vol. 2. Charles River Media, Hingham, pp 287–297
Tozour P (2002) The evolution of game AI. In: Rabin S (eds) AI game programming wisdom, 1st edn. Charles River Media, Hingham
Watkins C, Dayan P (1992) Q-learning. Mach Learn 8: 279–292
Whiteson S, Stone P, Stanley KO, Miikkulainen R, Kohl N (2005) Automatic feature selection in neuroevolution. In: Proceedings of the 2005 genetic and evolutionary computation conference. ACM Press, pp 1225–1232
Wolpert D, Sill J, Tumer K (2001) Reinforcement learning in distributed domains: beyond team games. In: Proceedings of the 17th international joint conference on artificial intelligence. Morgan Kaufmann, pp 819–824
Woodcock S (1998) Game AI: the state of the industry. Game Dev 5: 28–35
Woodcock S (1999) Game AI: The state of the industry. Game Dev 6: 34–43
Woodcock S (2000) Game AI: the state of the industry. Game Dev 7: 24–32
Woodcock S (2001) Game AI: the state of the industry 2000–2001. Game Dev 8: 36–44
Woodcock S (2002) Game AI: the state of the industry 2001–2002. Game Dev 9: 26–31
Yannakakis GN, Hallam J (2004) Evolving opponents for interesting interactive computer games. In: Schaal S, Ijspeert A, Billard A, Vijayakumar S, Hallam J, Meyer J-A (eds) From animals to animats 8: proceedings of the 8th international conference on simulation of adaptive behaviour. MIT Press, pp 499–508
Yannakakis GN, Levine J, Hallam J (2004) An evolutionary approach for interactive computer games. In: Proceedings of the 2004 IEEE congress on evolutionary computation. IEEE Press, pp 986–993
Yannakakis GN, Levine J, Hallam J, Papageorgiou M (2003) Performance, robustness and effort cost comparison of machine learning mechanisms in FlatLand. In: Proceedings of the 11th Mediterranean conference on control and automation. Rhodes, 18–20 June 2003
Yong CH, Stanley KO, Miikkulainen R, Karpov IV (2006) Incorporating advice into evolution of neural networks. In: Laird J, Schaeffer J (eds) Proceedings of the second artificial intelligence and interactive digital entertainment conference. AAAI Press, Menlo Park, pp 98–104
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Galway, L., Charles, D. & Black, M. Machine learning in digital games: a survey. Artif Intell Rev 29, 123–161 (2008). https://doi.org/10.1007/s10462-009-9112-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-009-9112-y