Iterated Boxed Pigs Game: A Reinforcement Learning Approach

Rudy Milani (), Maximilian Moll and Stefan Pickl
Additional contact information
Rudy Milani: Universität der Bundeswehr München
Maximilian Moll: Universität der Bundeswehr München
Stefan Pickl: Universität der Bundeswehr München

Chapter Chapter 74 in Operations Research Proceedings 2022, 2023, pp 617-623 from Springer

Abstract: Abstract This paper analyzes the iterated version of the well-known Boxed Pigs game through Reinforcement Learning. In this scenario, there are two differently sized players (pigs) that compete against each other. The core idea is about sacrificing a pay-off in order to generate some rewards. In our iterated version, these pigs play this game repeatedly using different strategies. We carry out two experiments: in the first one, we train two Q-learning agents against each other to see which equilibrium will be generated. In the second one, we pit the Reinforcement Learning agent against a fixed policy pig. The results of this experiment confirm the ability of Reinforcement Learning techniques in finding the best strategy for maximizing the return independently from the other player choices.

Keywords: Simulation; Prescriptive analytics; Machine learning (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-031-24907-5_74

Ordering information: This item can be ordered from
http://www.springer.com/9783031249075

DOI: 10.1007/978-3-031-24907-5_74

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().