Reinforcement-learning pricing algorithms sometimes converge to supra-competitive prices even in markets where collusion is impossible by design or cannot be an equilibrium outcome. We analyze when such spurious collusion may arise, and when instead the algorithms learn genuinely collusive strategies, focusing on the role of the rate and mode of exploration.

Algorithmic collusion: Genuine or spurious? / Calvano, Emilio; Calzolari, G; Denicolò, V; Pastorello, S. - In: INTERNATIONAL JOURNAL OF INDUSTRIAL ORGANIZATION. - ISSN 0167-7187. - 90:(2023), pp. 102973-102993. [10.1016/j.ijindorg.2023.102973]

Algorithmic collusion: Genuine or spurious?

Calvano, E;
2023

Abstract

Reinforcement-learning pricing algorithms sometimes converge to supra-competitive prices even in markets where collusion is impossible by design or cannot be an equilibrium outcome. We analyze when such spurious collusion may arise, and when instead the algorithms learn genuinely collusive strategies, focusing on the role of the rate and mode of exploration.
2023
Artificial intelligence, reinforcement learning, collusion, exploration
Algorithmic collusion: Genuine or spurious? / Calvano, Emilio; Calzolari, G; Denicolò, V; Pastorello, S. - In: INTERNATIONAL JOURNAL OF INDUSTRIAL ORGANIZATION. - ISSN 0167-7187. - 90:(2023), pp. 102973-102993. [10.1016/j.ijindorg.2023.102973]
File in questo prodotto:
File Dimensione Formato  
IJIO genuine or spurious editorial.pdf

Solo gestori archivio

Descrizione: editorial
Tipologia: Versione dell'editore
Licenza: Tutti i diritti riservati
Dimensione 821.54 kB
Formato Adobe PDF
821.54 kB Adobe PDF   Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11385/233563
Citazioni
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact