Comparing reinforcement learning approaches for solving game theoretic models: A dynamic airline pricing game example

Journal of the Operational Research Society

Volumn 63, Issue 8, 2012, Pages 1165-1173

  Collins, A ^a   Thomas, L ^b  

^a OLD DOMINION UNIVERSITY   (United States)

^b UNIVERSITY OF SOUTHAMPTON   (United Kingdom)

Author keywords

air transport; artificial intelligence; game theory; reinforcement learning

Indexed keywords

ARTIFICIAL INTELLIGENCE; COSTS; DECISION MAKING; GAME THEORY; MACHINE LEARNING;

AIR TRANSPORT; AIRLINE PRICING; ARTIFICIAL INTELLIGENCE TECHNIQUES; DECISION MAKERS; GAME-THEORETIC MODEL; NASH EQUILIBRIA; PRICING GAMES; REINFORCEMENT LEARNING APPROACH;

REINFORCEMENT LEARNING;

EID: 84863425031     PISSN: 01605682     EISSN: 14769360     Source Type: Journal    
DOI: 10.1057/jors.2011.94     Document Type: Article

References (41)

1. Ahmed AH and Poojari CA (2008). An overview of the issues in the airline industry and the role of optimization models and algorithms. J Opl Res Soc 59: 267-277. (Pubitemid 351334690)
2. Axelrod R (1997). The Complexity of Cooperation: Agent-based Models of Competition and Collaboration. Princeton University Press: Princeton.
3. Bellman R (1952). On the theory of dynamic programming. Proc Natl Acad Sci USA 38: 716-719.
4. Bertsekas DP and Tsitsiklis JN (1996). Neuro-dynamic Programming. Athena Scientific: Belmont.
5. Binmore K (1990). Essays on the Foundations of Game Theory. Basil Blackwell: Oxford.
6. Binmore K (1992). Fun and Games: A Text on Game Theory. Houghton Mifflin: Lexington.
7. Boyd EA (2007). Perspectives on the future of pricing. Presented at 7th Annual INFORMS Pricing and Revenue Management Conference, Barcelona, Spain.
8. Bridle JS (1990). Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters. In: Touretzky DS (ed). Advances in Neural Information Processing Systems: Proceedings of the 1989 Conference. Morgan Kaufmann: San Mateo, USA, pp 211-217.
9. Bryant JW (2007). Drama theory: Dispelling the myths. J Opl Res Soc 58: 602-613.
10. Chen X and Deng X (2005). Settling the complexity of 2-player Nash-Equilibrium. In Electronic Colloquium on Computational Complexity, 140(TR05), http://eccc.hpi-web.de/report/2005/140/accessed 1 June 2011.
11. Chen X and Zhan FB (2008). Agent-based modelling and simulation of urban evacuation: Relative effectiveness of simultaneous and staged evacuation strategies. J Opl Res Soc 59: 25-33. (Pubitemid 350261770)
12. Collins AJ (2009). Evaluating reinforcement learning for game theory application: Learning to price airline seats under competition. Ph.D. thesis, University of Southampton.
13. Collins AJ, Pullum F and Kenyon L (2003). Applications of game theory in defence project: Year one report. Dstl/CR07880, Defence Science and Technology Laboratories, Ministry of Defence, United Kingdom (UNCLASSIFIED).
14. Currie C, Cheng RCH and Smith HK (2008). Dynamic pricing of airline tickets with competition. J Opl Res Soc 59: 1026-1037.
15. Eatwell J, Milgate M and Newman P (eds) (1987). The New Palgrave: Game Theory. Macmillan Press: London.
16. Fudenberg D and Levine DK (1998). The Theory of Learning in Games. MIT Press: London.
17. Gosavi A (2003). Simulation-based Optimization: Parametric Optimization Techniques and Reinforcement Learning. Operations Research/Computer Science Interfaces Series. Kluwer Academic Publishers: London.
18. Harsanyi JC and Selten R (1988). A General Theory of Equilibrium Selection in Games. MIT Press: London.
19. Kim JS and Kwak TC (2007). Game theoretic analysis of the bargaining process over a long-term replenishment contract. J Opl Res Soc 58: 769-778. (Pubitemid 46782021)
20. Kolmogorov AN (1933). Sulla determinazione empirica di una legge di distribuzione. Giornale dell'Istituto Italiano degli Attuari 4: 83-91.
21. Lemke CE and Howson JJT (1964). Equilibrium points of bimatrix games. SIAM J Appl Math 12: 413-423.
22. Leslie AM (2001). Learning: Association or computation? Introduction to a special section. Curr Dir Psychol Sci 10(4): 124-127. (Pubitemid 33388536)
23. Leslie DS and Collins EJ (2005). Individual q-learning in normal form games. SIAM J Control Optim 44: 495-414.
24. Luce RD (1959). Individual Choice Behaviour. Wiley: Oxford.
25. Mannor S and Shamma J (2007). Multi-agent learning for engineers. Artificial Intelligence 171: 417-422. (Pubitemid 46802418)
26. Manski CF (1977). The structure of random utility models. Theory and Decision 8: 229-254.
27. McKelvey RD, McLennan AM and Turocy TL (2007). Gambit: Software tools for Game Theory - Version 0.2007.01.30, http://econweb.tamu.edu/gambit, accessed 10 September 2008.
28. Michie D and Chambers RA (1968). BOXES: An experiment in adaptive control. In: Dale E and Michie D (eds). Machine Intelligence. Vol. 2, Oliver and Boyd: Edinburgh, pp 137-152.
29. Minsky ML (1954). Theory of neural-analog reinforcement systems and its application to the brain-model problem. Ph.D. dissertation, Princeton University.
30. Nash J (1951). Non-cooperative games. Ann Math 54: 286-295.
31. North MJ and Macal CM (2007). Managing Business Complexity: Discovering Strategic Solutions with Agent-based Modeling and Simulation. Oxford University Press: Oxford.
32. Pidd M (1996). Tools for Thinking: Modelling in Management Science. Wiley: Chichester.
33. Rummery GA (1995). Problem solving with reinforcement learning. Ph.D. thesis, Cambridge University.
34. Shoham Y, Powers R and Grenager T (2004). Multi-agent reinforcement learning: A critical survey. Presented at the AAAI Fall Symposium on Artificial Multi-agent Learning. Washington DC, USA.
35. Sutton RS and Barto AG (1998). Reinforcement Learning: An Introduction. MIT Press: London.
36. Talluri KT and van Ryzin GJ (2004). Theory and Practice of Revenue Management. Springer-Verlag: New York.
37. Thorndike EL (1911). Animal Intelligence. Hafner: Darien.
38. von Stackelberg HF (1934). Marktform und Gleichgewicht. Julius Springer: Vienna.
39. von Stengel B (2002). Computing equilibria for two-person games. In: Aumann RJ and Hart S (eds). Handbook of Game Theory with Economic Applications. Vol. 3, Elsevier: Amsterdam, pp 1723-1759.
40. Watkins CJCH (1989). Learning from delayed rewards. Ph.D. thesis, Cambridge University.
41. Wauters T, Verbeeck K, Vanden Berghe G and De Causmaecker P (2011). Learning agents for the multi-mode project scheduling problem. J Opl Res Soc 62: 281-290.