Computational Performance of Deep Reinforcement Learning to find Nash Equilibria

Abstract

We test the performance of deep deterministic policy gradient (DDPG)-a deep reinforcement learning algorithm, able to handle continuous state and action spaces-to learn Nash equilibria in a setting where firms compete in prices. These algorithms are typically considered "model-free" because they do not require transition probability functions (as in e.g., Markov games) or predefined functional forms. Despite being "model-free", a large set of parameters are utilized in various steps of the algorithm. These are e.g., learning rates, memory buffers, state-space dimensioning, normalizations, or noise decay rates and the purpose of this work is to systematically test the effect of these parameter configurations on convergence to the analytically derived Bertrand equilibrium.We find parameter choices that can reach convergence rates of up to 99%. The reliable convergence may make the method a useful tool to study strategic behavior of firms even in more complex settings.

RangL: A Reinforcement Learning Competition Platform

“…In particular, the team employed the deep deterministic policy gradient (DDPG) method [13,14]. Lanterne opted for DDPG since the team had already analyzed its suitability to find Nash equilbria in uniform price auctions and validated DDPG intensely against classical game theoretic predictions [15].…”