No-regret Learning in Cournot Games
arXiv:1906.06612
Abstract
This paper examines the convergence of no-regret learning in Cournot games with continuous actions. Cournot games are the essential model for many socio-economic systems, where players compete by strategically setting their output quantity. We assume that players do not have full information of the game and thus cannot pre-compute a Nash equilibrium. Two types of feedback are considered: one is bandit feedback and the other is gradient feedback. To study the convergence of the induced sequence of play, we introduce the notion of convergence in measure, and show that the players' actual sequence of action converges to the unique Nash equilibrium. In addition, our results naturally extend the no-regret learning algorithms' time-average regret bounds to obtain the final-iteration convergence rates. Together, our work presents significantly sharper convergence results for learning in games without strong assumptions on game property (e.g., monotonicity) and shows how exploiting the game information feedback can influence the convergence rates.
References in corpus (6)
- Fast Convergence of Regularized Learning in Games
- Competition and Coalition Formation of Renewable Power Producers
- Learning in Games: Robustness of Fast Convergence
- Bandit learning in concave -person games
- Finding Friend and Foe in Multi-Agent Games
- Optimal Resource Allocation over Networks via Lottery-Based Mechanisms