A reinforcement learning approach to a single leg airline revenue management problem with multiple fare classes and overbooking

IIE Transactions (Institute of Industrial Engineers)

Volumn 34, Issue 9, 2002, Pages 729-742

  Gosavi, Abhijit ^a   Bandla, Naveen ^b   Das, Tapas K ^c  

^a Malik and Seeme Hasan School of Business   (United States)

^b Research Group   (United States)

^c University of South Florida   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AIR TRANSPORTATION; COMPUTER SIMULATION; DECISION THEORY; DYNAMIC PROGRAMMING; LEARNING ALGORITHMS; LOGISTICS; MARKOV PROCESSES; MATHEMATICAL MODELS; OPERATIONS RESEARCH; RESERVATION SYSTEMS; SENSITIVITY ANALYSIS; STATE SPACE METHODS;

FARE CLASSES; LARGE SCALE STOCHASTIC OPTIMIZATION; OVERBOOKING; REINFORCEMENT LEARNING; REVENUE MANAGEMENT; SEMI-MARKOV DECISION PROBLEM;

OPTIMIZATION;

EID: 0036722536     PISSN: 0740817X     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1015583703449     Document Type: Article

References (34)

1. Stochastic approximation for non-expansive maps: Application to Q-learning algorithms
2. Airline yield management using a reinforcement learning approach
3. The theory of dynamic programming
4. Application of a probabilistic decision model to airline seat inventory control
5. Airline seat allocation with multiple nested fare classes
6. Multiperiod airline overbooking with a single fare class
7. Optimal airline seat allocation with fare classes nested by origins and destinations
8. Learning rate schedules for faster stochastic gradient search
9. Solving semi-Markov decision problems using average reward reinforcement learning
10. Airline ties profitability yield to management
11. The passenger-mix problem in the scheduled airlines
12. An algorithm for solving semi-Markov decision problems using reinforcement learning: Convergence analysis and numerical results
13. Stochastic decomposition: An algorithm for two-stage linear programs with recourse
14. Forecasting and control of passenger bookings
15. Automatic booking level control
16. Revenue management: Research overview and prospects
17. A stochastic approximation method
18. Optimal and approximate control policies for airline booking with sequential nonmonotonic fare classes
19. Stochastic programming by Monte Carlo methods
20. Yield management at American airlines
21. Airline yield management with overbooking, cancellations and no-shows
22. Learning to predict by the methods of temporal differences
23. Bid-price controls for network revenue management
24. Statistical problems in airline reservation control
25. Revenue management without forecasting or optimization: An adaptive algorithm for determining seat protection levels
26. Learning from delayed rewards
27. Decentralized learning in finite Markov chains
28. An airline seat management model for a single leg route when lower fare classes book first