An Online Learning Approach to a Multi-player N-armed Functional Bandit
Book chapter
Sam O’Neill, Ovidiu Bagdasar and Antonio Liotta 2020. An Online Learning Approach to a Multi-player N-armed Functional Bandit. in: Numerical Computations: Theory and Algorithms Springer. pp. 438 - 445
Authors | Sam O’Neill, Ovidiu Bagdasar and Antonio Liotta |
---|---|
Abstract | Congestion games possess the property of emitting at least one pure Nash equilibrium and have a rich history of practical use in transport modelling. In this paper we approach the problem of modelling equilibrium within congestion games using a decentralised multi-player probabilistic approach via stochastic bandit feedback. Restricting the strategies available to players under the assumption of bounded rationality, we explore an online multiplayer exponential weights algorithm for unweighted atomic routing games and compare this with a ϵ |
Keywords | Congestion games; Multi-armed bandit; Online learning |
Page range | 438 - 445 |
Year | 2020 |
Book title | Numerical Computations: Theory and Algorithms |
Publisher | Springer |
Edition | 1st |
Series | Lecture Notes in Computer Science (LNCS, volume 11973) |
ISBN | 978-3-030-40616-5 |
ISSN | 1611-3349 |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-40616-5_41 |
Web address (URL) | https://doi.org/10.1007/978-3-030-40616-5_41 |
https://link.springer.com/book/10.1007/978-3-030-39081-5#keywords | |
Output status | Published |
Publication dates | |
Online | 13 Feb 2020 |
14 Feb 2020 | |
Publication process dates | |
Deposited | 25 May 2023 |
Permalink -
https://repository.derby.ac.uk/item/9yyw8/an-online-learning-approach-to-a-multi-player-n-armed-functional-bandit
21
total views0
total downloads1
views this month0
downloads this month