Reinforcement Learning, Collusion, and the Folk Theorem
G Askenazi-Golan, DM Cecchelli, E Plumb - arXiv preprint arXiv …, 2024 - arxiv.org
We explore the behaviour emerging from learning agents repeatedly interacting strategically
for a wide range of learning dynamics that includes projected gradient, replicator and log …
for a wide range of learning dynamics that includes projected gradient, replicator and log …
Local (coarse) correlated equilibria in non-concave games
MŞ Ahunbay - arXiv preprint arXiv:2403.18174, 2024 - arxiv.org
We investigate local notions of correlated equilibria, distributions of actions for smooth
games such that players do not incur any regret against modifications of their strategies …
games such that players do not incur any regret against modifications of their strategies …