Computational Performance of Deep Reinforcement Learning to Find Nash Equilibria

نویسندگان

چکیده

Abstract We test the performance of deep deterministic policy gradient—a reinforcement learning algorithm, able to handle continuous state and action spaces—to find Nash equilibria in a setting where firms compete offer prices through uniform price auction. These algorithms are typically considered “model-free” although large set parameters is utilized by algorithm. may include rates, memory buffers, space dimensioning, normalizations, or noise decay purpose this work systematically effect these parameter configurations on convergence analytically derived Bertrand equilibrium. choices that can reach rates up 99%. show algorithm also converges more complex settings with multiple players different cost structures. Its reliable make method useful tool studying strategic behavior even settings.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning strict Nash equilibria through reinforcement

This paper studies the analytical properties of the reinforcement learning model proposed in Erev and Roth (1998), also termed cumulative reinforcement learning in Laslier et al. (2001). The main results of the paper show that, if the solution trajectories of the underlying replicator equation converge exponentially fast, then, with probability arbitrarily close to one, all the pathwise realiza...

متن کامل

Relaxation algorithms to find Nash equilibria with economic applications

Recent theoretical studies have shown that a relaxation algorithm can be used to find noncooperative equilibria of synchronous infinite games with nonlinear payoff functions and coupled constraints. In this study, we introduce an improvement to the algorithm, such as the steepest-descent step-size control, for which the convergence of the algorithm is proved. The algorithm is then tested on sev...

متن کامل

The Computational Complexity of Nash Equilibria

Game theory has grown in importance as academics from all fields have realized the importance of strategy in domains of human behavior ranging from business to the Internet. The computational issues of game theory are important to both a game’s participants and designers. A participant in a game, or their consultant, obviously wants to compute their optimal moves in anticipation of their opppon...

متن کامل

Computing Nash equilibria through computational intelligence methods

Nash equilibrium constitutes a central solution concept in game theory. The task of detecting the Nash equilibria of a finite strategic game remains a challenging problem up-to-date. This paper investigates the effectiveness of three computational intelligence techniques, namely, covariance matrix adaptation evolution strategies, particle swarm optimization, as well as, differential evolution, ...

متن کامل

Operation Scheduling of MGs Based on Deep Reinforcement Learning Algorithm

: In this paper, the operation scheduling of Microgrids (MGs), including Distributed Energy Resources (DERs) and Energy Storage Systems (ESSs), is proposed using a Deep Reinforcement Learning (DRL) based approach. Due to the dynamic characteristic of the problem, it firstly is formulated as a Markov Decision Process (MDP). Next, Deep Deterministic Policy Gradient (DDPG) algorithm is presented t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Computational Economics

سال: 2023

ISSN: ['1572-9974', '0927-7099']

DOI: https://doi.org/10.1007/s10614-022-10351-6