paper-with-me

Papers

Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees

2022-01-31 · Mo Zhou, Jianfeng Lu

We propose a single time-scale actor-critic algorithm to solve the linear quadratic regulator (LQR) problem. A least squares temporal difference (LSTD) method is applied to the critic and a natural policy gradient method is used for the actor. We give a proof of convergence with sample complexity $\mathcal{O}(\varepsilon^{-1} \log(\varepsilon^{-1})^2)$. The method in the proof is applicable to general single time-scale bilevel optimization problem. We also numerically validate our theoretical results on the convergence.

📄 PDF Abstract BibTeX arXiv:2202.00048

Code (0)

등록된 구현이 없습니다.

Tasks

Bilevel Optimization

Similar Papers 제목 키워드 기반

Finite-time analysis of single-timescale actor-critic

2022-10-18 · NeurIPS 2023 11 · Xuyang Chen, Lin Zhao

Actor-critic methods have achieved significant success in many challenging applications. However, its finite-time convergence is still poorly understood in the most practical single-timescale form. Existing works on anal…

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…

Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation

2021-06-14 · Anas Barakat, Pascal Bianchi, Julien Lehmann

Actor-critic methods integrating target networks have exhibited a stupendous empirical success in deep reinforcement learning. However, a theoretical understanding of the use of target networks in actor-critic methods is…

Deep Reinforcement Learning

Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic

2022-06-12 · Qijun Luo, Xiao Li

Decentralized Actor-Critic (AC) algorithms have been widely utilized for multi-agent reinforcement learning (MARL) and have achieved remarkable success. Apart from its empirical success, the theoretical convergence prope…

Multi-agent Reinforcement LearningPrivacy Preserving

A Small Gain Analysis of Single Timescale Actor Critic

2022-03-04 · Alex Olshevsky, Bahman Gharesifard

We consider a version of actor-critic which uses proportional step-sizes and only one critic update with a single sample from the stationary distribution per actor step. We provide an analysis of this method using the sm…