Gradient play in stochastic games: stationary points, convergence, and sample complexity

• URL: http://arxiv.org/abs/2106.00198v5
• Date: Wed, 6 Dec 2023 21:33:55 GMT
• Title: Gradient play in stochastic games: stationary points, convergence, and sample complexity
• Authors: Runyu Zhang, Zhaolin Ren, Na Li
• Abstract summary: We study the performance of the gradient play algorithm for games (SGs) We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting. For a subclass of SGs called Markov potential games, we design a sample-based reinforcement learning algorithm.
• Score: 6.97785632069611
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the performance of the gradient play algorithm for stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is shared between agents. Policies are directly parameterized by the probability of choosing a certain action at a given state. We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a local convergence rate around strict NEs. Further, for a subclass of SGs called Markov potential games (which includes the setting with identical rewards as an important special case), we design a sample-based reinforcement learning algorithm and give a non-asymptotic global convergence rate analysis for both exact gradient play and our sample-based learning algorithm. Our result shows that the number of iterations to reach an $\epsilon$-NE scales linearly, instead of exponentially, with the number of agents. Local geometry and local stability are also considered, where we prove that strict NEs are local maxima of the total potential function and fully-mixed NEs are saddle points.

Related papers

• PAPAL: A Provable PArticle-based Primal-Dual ALgorithm for Mixed Nash Equilibrium [58.26573117273626]
  We consider the non-AL equilibrium nonconptotic objective function in two-player zero-sum continuous games. Our novel insights into the particle-based algorithms for continuous distribution strategies are presented.
  arXiv  Detail & Related papers  (2023-03-02T05:08:15Z)
• Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence [30.084357461497042]
  We learn a Nash equilibrium of an MPG in which the size of state space and/or the number of players can be very large. We propose new independent policy gradient algorithms that are run by all players in tandem. We identify a class of independent policy gradient algorithms that enjoys convergence for both zero-sum Markov games and Markov cooperative games with the players that are oblivious to the types of games being played.
  arXiv  Detail & Related papers  (2022-02-08T20:09:47Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games [3.441021278275805]
  Learning in games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL) We establish the finite-sample complexity of fully decentralized Q-learning algorithms in a significant class of general approximation games (SGs) We focus on the practical while challenging setting of fully decentralized MARL, where neither the rewards nor the actions of other agents can be observed by each agent.
  arXiv  Detail & Related papers  (2021-12-15T03:33:39Z)
• Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond [63.59034509960994]
  We study shuffling-based variants: minibatch and local Random Reshuffling, which draw gradients without replacement. For smooth functions satisfying the Polyak-Lojasiewicz condition, we obtain convergence bounds which show that these shuffling-based variants converge faster than their with-replacement counterparts. We propose an algorithmic modification called synchronized shuffling that leads to convergence rates faster than our lower bounds in near-homogeneous settings.
  arXiv  Detail & Related papers  (2021-10-20T02:25:25Z)
• A Stochastic Newton Algorithm for Distributed Convex Optimization [62.20732134991661]
  We analyze a Newton algorithm for homogeneous distributed convex optimization, where each machine can calculate gradients of the same population objective. We show that our method can reduce the number, and frequency, of required communication rounds compared to existing methods without hurting performance.
  arXiv  Detail & Related papers  (2021-10-07T17:51:10Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)
• Computational Performance of Deep Reinforcement Learning to find Nash Equilibria [0.0]
  We use a deep reinforcement learning algorithm to learn Nash equilibria in a setting where firms compete in prices. Despite being model-free, a large set of parameters are utilized in various steps of the algorithm. We find parameter choices that can reach convergence rates of up to 99%.
  arXiv  Detail & Related papers  (2021-04-26T22:14:17Z)
• Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance [0.0]
  In this paper, a general optimization procedure is studied, unifying several variants of the gradient descent such as, among others, the heavy ball method, the Nesterov Accelerated Gradient (S-NAG), and the widely used Adam method. The avoidance is studied as a noisy discretization of a non-autonomous ordinary differential equation.
  arXiv  Detail & Related papers  (2020-12-07T19:14:49Z)
• Sinkhorn Natural Gradient for Generative Models [125.89871274202439]
  We propose a novel Sinkhorn Natural Gradient (SiNG) algorithm which acts as a steepest descent method on the probability space endowed with the Sinkhorn divergence. We show that the Sinkhorn information matrix (SIM), a key component of SiNG, has an explicit expression and can be evaluated accurately in complexity that scales logarithmically. In our experiments, we quantitatively compare SiNG with state-of-the-art SGD-type solvers on generative tasks to demonstrate its efficiency and efficacy of our method.
  arXiv  Detail & Related papers  (2020-11-09T02:51:17Z)
• Multi-Agent Reinforcement Learning in Stochastic Networked Systems [30.78949372661673]
  We study multi-agent reinforcement learning (MARL) in a network of agents. The objective is to find localized policies that maximize the (discounted) global reward.
  arXiv  Detail & Related papers  (2020-06-11T16:08:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.