Clemens Possnig

collaborators

2 papers

cs.GT2026

The Bounds of Algorithmic Collusion; $Q$ -learning, Gradient Learning, and the Folk Theorem

Galit Askenazi-Golan, Domenico Mergoni Cecchelli, Edward Plumb +1

We explore the behaviour emerging from learning agents repeatedly interacting strategically for a wide range of learning dynamics, including $Q$ -learning, projected gradient, repli…

econ.TH2026

The Algorithmic Advantage: How Reinforcement Learning Generates Rich Communication

Emilio Calvano, Clemens Possnig, Juha Tolvanen

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 Cr…

The Bounds of Algorithmic Collusion; Q-learning, Gradient Learning, and the Folk Theorem

The Algorithmic Advantage: How Reinforcement Learning Generates Rich Communication

The Bounds of Algorithmic Collusion; $Q$ -learning, Gradient Learning, and the Folk Theorem