paper-with-me

Papers

Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning

2025-05-24 · Zhiyao Zhang, Myeung Suk Oh, FNU Hairi, Ziyue Luo, Alvaro Velasquez, Jia Liu

Actor-critic methods for decentralized multi-agent reinforcement learning (MARL) facilitate collaborative optimal decision making without centralized coordination, thus enabling a wide range of applications in practice. To date, however, most theoretical convergence studies for existing actor-critic decentralized MARL methods are limited to the guarantee of a stationary solution under the linear function approximation. This leaves a significant gap between the highly successful use of deep neural actor-critic for decentralized MARL in practice and the current theoretical understanding. To bridge this gap, in this paper, we make the first attempt to develop a deep neural actor-critic method for decentralized MARL, where both the actor and critic components are inherently non-linear. We show that our proposed method enjoys a global optimality guarantee with a finite-time convergence rate of O(1/T), where T is the total iteration times. This marks the first global convergence result for deep neural actor-critic methods in the MARL literature. We also conduct extensive numerical experiments, which verify our theoretical results.

📄 PDF Abstract BibTeX arXiv:2505.18433

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingMulti-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator

2022-08-18 · Xuyang Chen, Jingliang Duan, Yingbin Liang, Lin Zhao

The actor-critic (AC) reinforcement learning algorithms have been the powerhouse behind many challenging applications. Nevertheless, its convergence is fragile in general. To study its instability, existing works mostly …

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

2021-11-04 · NeurIPS 2023 11 · Shangtong Zhang, Remi Tachet, Romain Laroche

In this paper, we establish the global optimality and convergence rate of an off-policy actor critic algorithm in the tabular setting without using density ratio to correct the discrepancy between the state distribution …

Policy Gradient Methods

Neural Policy Gradient Methods: Global Optimality and Rates of Convergence

2019-08-29 · ICLR 2020 1 · Lingxiao Wang, Qi Cai, Zhuoran Yang, Zhaoran Wang

Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such "neur…

Policy Gradient Methods

Unichain and Aperiodicity are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits

2024-02-08 · Yige Hong, Qiaomin Xie, Yudong Chen, Weina Wang

We consider the infinite-horizon, average-reward restless bandit problem in discrete time. We propose a new class of policies that are designed to drive a progressively larger subset of arms toward the optimal distributi…

Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy

2020-08-02 · ICLR 2021 1 · Zuyue Fu, Zhuoran Yang, Zhaoran Wang

We study the global convergence and global optimality of actor-critic, one of the most popular families of reinforcement learning algorithms. While most existing works on actor-critic employ bi-level or two-timescale upd…