arXiv q-fin· Kaue Lopes de Moraes, Rodrigo De-Losso·· 2 days agoAI Score58
Algorithmic Collusion Without Deterrence: Auditing Punishment Mechanisms in Q-Learning Pricing Agents
Algorithmic Collusion Without Deterrence: Auditing the Punishment Mechanism in Q-Learning Pricing Agents
AI summary
This arXiv paper reproduces Calvano et al.'s 2020 simulated Bertrand duopoly Q-learning pricing experiment and challenges the conventional punishment-mechanism explanation for why independently trained tabular Q-learning agents converge to supracompetitive prices.
Source:arXiv q-fin · arxiv.org
Machine LearningHigh-Frequency and Market MicrostructurePaper Research#Papers / Research#Machine Learning#High-Frequency / Market Microstructure#arXiv