The Algorithmic Advantage: How Reinforcement Learning Generates Rich Communication

Emilio Calvano (), Clemens Possnig () and Juha Tolvanen ()
Additional contact information
Emilio Calvano: Department of Economics and Financial Markets, Luiss University
Clemens Possnig: School of Economics, University of Waterloo
Juha Tolvanen: Department of Economics and Finance, University of Rome Tor Vergata

No 26001, Working Papers from University of Waterloo, Department of Economics

Abstract: We analyze strategic communication when advice is generated by a reinforcement-learning algorithm rather than by a fully rational sender. Building on the cheap-talk framework of Crawford and Sobel (1982), an advisor adapts its messages based on payoff feedback, while a decision maker best-responds. We provide a theoretical analysis of the long-run communication outcomes induced by such reward-driven adaptation. With aligned preferences, we establish that learning robustly leads to informative communication even from uninformative initial policies. With misaligned preferences, no stable outcome exists; instead, learning generates cycles that sustain highly informative communication and payoffs exceeding those of any static equilibrium.

Keywords: strategic communication; reinforcement-learning algorithm (search for similar items in EconPapers)
Pages: 33 pages
Date: 2026-02-12
New Economics Papers: this item is included in nep-mic
References: Add references at CitEc
Citations:

Forthcoming

Downloads: (external link)
https://hdl.handle.net/10012/23582 First version, 2026 (application/pdf)

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:wat:wpaper:26001

Access Statistics for this paper

More papers in Working Papers from University of Waterloo, Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sherri Anne Arsenault ().