Reinforcement Learning for Stochastic Networks, Toulouse

Session

Parallel session: Algorithmic collusion: Foundations for understanding the emergence of anticompetitive behaviour

Jun 20, 2024, 1:30 PM

A001 (ENSEEIHT)

Description

Organizer and chair: Janusz Meylahn

35. Reinforcement learning in a prisoner's dilemma

Artur Dolgopolov (Bielefeld University)

6/20/24, 1:30 PM

I characterize the outcomes of a class of model-free reinforcement learning algorithms, such as stateless Q-learning, in a prisoner's dilemma. The behavior is studied in the limit as players stop experimenting after sufficiently exploring their options. A closed form relationship between the learning rate and game payoffs reveals whether the players will learn to cooperate or defect. The...

36. Less than meets the eye: simultaneous experiments as a source of algorithmic seeming collusion

Xavier Lambin (ESSEC Business School)

6/20/24, 2:00 PM

This article challenges the idea of algorithmic collusion as proposed in Calvano et al. (2020) and subsequent literature. Identifying a critical mistake, we dispute the notion that supracompetitive prices result from collusive mechanisms where high prices are sustained by reward and punishment strategies. Instead, our analysis suggests that both phenomena originate from simultaneous...

31. Quantifying the likelihood of collusion by provably convergent reinforcement learning

Janusz Meylahn (University of Twente)

6/20/24, 2:30 PM

Recent advances in decentralized multiagent reinforcement learning (MARL) have led to the development of algorithms that are provably convergent in a variety of Markov game subclasses. One of these is the Decentralized Q-learning (DQ) algorithm by Arslan and Yüksel (2017) which is provably convergent in weakly acyclic games. In this talk, I will present a new characterization of weak...