Comparing reinforcement learning approaches for solving game theoretic models: a dynamic airline pricing game example
Comparing reinforcement learning approaches for solving game theoretic models: a dynamic airline pricing game example
Due to the difficulty in solving game theoretic models, there is a tendency to focus on the overly simplistic dynamic airline pricing games or to even ignore competition completely. Recent changes to the industry mean that airlines can no longer ignore competitors in their model. This paper adds more complex customer model aspects; i.e., customer choice using a Logit model, customer demand using a linear probabilistic demand model, and market size using a binary random function; into an existing solvable game that only had a simple customer model. A reinforcement learning method was used to solve the newly formed games with mixed results.
game theory, artificial intelligence, reinforcement learning, air transport
1165-1173
Collins, A.J.
1d1da68c-91a0-49f0-9b19-2d63273c568d
Thomas, Lyn C.
a3ce3068-328b-4bce-889f-965b0b9d2362
August 2012
Collins, A.J.
1d1da68c-91a0-49f0-9b19-2d63273c568d
Thomas, Lyn C.
a3ce3068-328b-4bce-889f-965b0b9d2362
Collins, A.J. and Thomas, Lyn C.
(2012)
Comparing reinforcement learning approaches for solving game theoretic models: a dynamic airline pricing game example.
Journal of the Operational Research Society, 63, .
(doi:10.1057/jors.2011.94).
Abstract
Due to the difficulty in solving game theoretic models, there is a tendency to focus on the overly simplistic dynamic airline pricing games or to even ignore competition completely. Recent changes to the industry mean that airlines can no longer ignore competitors in their model. This paper adds more complex customer model aspects; i.e., customer choice using a Logit model, customer demand using a linear probabilistic demand model, and market size using a binary random function; into an existing solvable game that only had a simple customer model. A reinforcement learning method was used to solve the newly formed games with mixed results.
Text
jorscomparing_reinforcement.html
- Version of Record
Restricted to Repository staff only
More information
e-pub ahead of print date: December 2011
Published date: August 2012
Keywords:
game theory, artificial intelligence, reinforcement learning, air transport
Organisations:
Centre of Excellence for International Banking, Finance & Accounting
Identifiers
Local EPrints ID: 343123
URI: http://eprints.soton.ac.uk/id/eprint/343123
ISSN: 0160-5682
PURE UUID: 4670cd9c-7bd7-4e54-b7ff-437f325039a2
Catalogue record
Date deposited: 24 Sep 2012 15:19
Last modified: 14 Mar 2024 12:00
Export record
Altmetrics
Contributors
Author:
A.J. Collins
Author:
Lyn C. Thomas
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics