works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

econ.TH2026

Auditing Algorithmic Collusion from Strategy Graphs

Nicolas Eschenbaum, Janusz M. Meylahn

Detecting algorithmic collusion is challenging because regulators often have limited access to firms' algorithms, training data, and market information. We study an intermediate-in…

cs.MA2026

Equilibrium stability as a driver of cooperation among Q-learners

Janusz M. Meylahn, Maximilian Schäfer

The paper analyzes how Q‑learning agents that keep a constant level of exploration spend time playing cooperative strategies in repeated Prisoner's Dilemma games, deriving a predic…

stat.ML2026

Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under -Mixing

Leon Halgryn, Sophie Langer, Janusz M. Meylahn +1

Finite-sample analyses of deep Q-learning typically treat replayed data as independent, even though it is sampled from temporally dependent state-action trajectories. We study the…

physics.soc-ph2024

Risk aversion can promote cooperation

Jay Armas, Wout Merbis, Janusz Meylahn +2

Cooperative dynamics are central to our understanding of many phenomena in living and complex systems. However, we lack a universal mechanism to explain the emergence of cooperatio…

physics.soc-ph2024

How social reinforcement learning can lead to metastable polarisation and the voter model

Benedikt V. Meylahn, Janusz M. Meylahn

Previous explanations for the persistence of polarization of opinions have typically included modelling assumptions that predispose the possibility of polarization (i.e., assumptio…