Learning to Control Unknown Strongly Monotone Games

• URL: http://arxiv.org/abs/2407.00575v1
• Date: Sun, 30 Jun 2024 03:33:42 GMT
• Title: Learning to Control Unknown Strongly Monotone Games
• Authors: Siddharth Chandak, Ilai Bistritz, Nicholas Bambos,
• Abstract summary: We propose a simple algorithm that learns to shift the NE of the game to meet the linear constraints by adjusting the controlled coefficients online. We prove that our algorithm, which is based on two time-scale approximation, guarantees convergence with probability 1 to the set of NE that meet target linear constraints. We demonstrate how our scheme can be applied to optimizing a global quadratic cost at NE and load balancing in resource allocation games.
• Score: 16.327788209492805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Consider $N$ players each with a $d$-dimensional action set. Each of the players' utility functions includes their reward function and a linear term for each dimension, with coefficients that are controlled by the manager. We assume that the game is strongly monotone, so if each player runs gradient descent, the dynamics converge to a unique Nash equilibrium (NE). The NE is typically inefficient in terms of global performance. The resulting global performance of the system can be improved by imposing $K$-dimensional linear constraints on the NE. We therefore want the manager to pick the controlled coefficients that impose the desired constraint on the NE. However, this requires knowing the players' reward functions and their action sets. Obtaining this game structure information is infeasible in a large-scale network and violates the users' privacy. To overcome this, we propose a simple algorithm that learns to shift the NE of the game to meet the linear constraints by adjusting the controlled coefficients online. Our algorithm only requires the linear constraints violation as feedback and does not need to know the reward functions or the action sets. We prove that our algorithm, which is based on two time-scale stochastic approximation, guarantees convergence with probability 1 to the set of NE that meet target linear constraints. We then provide a mean square convergence rate of $O(t^{-1/4})$ for our algorithm. This is the first such bound for two time-scale stochastic approximation where the slower time-scale is a fixed point iteration with a non-expansive mapping. We demonstrate how our scheme can be applied to optimizing a global quadratic cost at NE and load balancing in resource allocation games. We provide simulations of our algorithm for these scenarios.

Related papers

• Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback [75.29048190099523]
  Online gradient descent (OGD) is well known to be doubly optimal under strong convexity or monotonicity assumptions. In this paper, we design a fully adaptive OGD algorithm, textsfAdaOGD, that does not require a priori knowledge of these parameters.
  arXiv  Detail & Related papers  (2023-10-21T18:38:13Z)
• Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning [105.7510838453122]
  We examine online safe multi-agent reinforcement learning using constrained Markov games. We develop an upper confidence reinforcement learning algorithm to solve this Lagrangian problem. Our algorithm updates the minimax decision primal variables via online mirror descent and the dual variable via projected gradient step.
  arXiv  Detail & Related papers  (2023-05-31T22:09:24Z)
• Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms [66.8634598612777]
  We show that Nash equilibrium (NE) is acceptable to all players in a multi-player game. We also show that no one can benefit unilaterally from the general theory step by step.
  arXiv  Detail & Related papers  (2023-01-19T11:36:50Z)
• Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers? [156.5760265539888]
  We study multi-player general-sum Markov games with one of the players designated as the leader and the other players regarded as followers. For such a game, our goal is to find a Stackelberg-Nash equilibrium (SNE), which is a policy pair $(pi*, nu*)$. We develop sample-efficient reinforcement learning (RL) algorithms for solving for an SNE in both online and offline settings.
  arXiv  Detail & Related papers  (2021-12-27T05:41:14Z)
• Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback [29.553652241608997]
  We study the class of textitsmooth and strongly monotone games and study optimal no-regret learning therein. We first construct a new bandit learning algorithm and show that it achieves the single-agent optimal regret of $tildeTheta(nsqrtT)$. Our results thus settle this open problem and contribute to the broad landscape of bandit game-theoretical learning.
  arXiv  Detail & Related papers  (2021-12-06T08:27:54Z)
• Towards convergence to Nash equilibria in two-team zero-sum games [17.4461045395989]
  Two-team zero-sum games are defined as multi-player games where players are split into two competing sets of agents. We focus on the solution concept of Nash equilibria (NE) We show that computing NE for this class of games is $textithard$ for the complexity class $mathrm$.
  arXiv  Detail & Related papers  (2021-11-07T21:15:35Z)
• Towards General Function Approximation in Zero-Sum Markov Games [126.58493169301012]
  This paper considers two-player zero-sum finite-horizon Markov games with simultaneous moves. Provably efficient algorithms for both decoupled and coordinated settings are developed.
  arXiv  Detail & Related papers  (2021-07-30T15:25:13Z)
• Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall [34.73929457960903]
  We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play. We provide the Implicit Exploration Online Mirror Descent (IXOMD) algorithm. IXOMD is a model-free algorithm with a high-probability bound on the convergence rate to the NE of order $1/sqrtT$ where $T$ is the number of played games.
  arXiv  Detail & Related papers  (2021-06-11T09:51:29Z)
• Almost Optimal Algorithms for Two-player Markov Games with Linear Function Approximation [92.99933928528797]
  We study reinforcement learning for two-player zero-sum Markov games with simultaneous moves. We propose an algorithm Nash-UCRL-VTR based on the principle "Optimism-in-Face-of-Uncertainty" We show that Nash-UCRL-VTR can provably achieve an $tildeO(dHsqrtT)$ regret, where $d$ is the linear function dimension.
  arXiv  Detail & Related papers  (2021-02-15T09:09:16Z)
• Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent [40.99558326586079]
  A class of non-concave zero-sum games functions hidden zero-sum games. We prove convergence to the von-Neumann equilibrium of the "hidden" convex-concave game. Our guarantees are non-local, which as far as we know is a first-of-its-kind type of result in non-concave games.
  arXiv  Detail & Related papers  (2021-01-13T18:13:49Z)
• Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium [116.56359444619441]
  We develop provably efficient reinforcement learning algorithms for two-player zero-sum finite-horizon Markov games. In the offline setting, we control both players and aim to find the Nash Equilibrium by minimizing the duality gap. In the online setting, we control a single player playing against an arbitrary opponent and aim to minimize the regret.
  arXiv  Detail & Related papers  (2020-02-17T17:04:16Z)

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.