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