paper-with-me

홈 › Papers

Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost

2019-12-01 · NeurIPS 2019 12 · Zhuoran Yang, Yongxin Chen, Mingyi Hong, Zhaoran Wang

Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus on its application to linear quadratic regulators, a simple yet fundamental setting of reinforcement learning. We establish a nonasymptotic convergence analysis of actor- critic in this setting. In particular, we prove that actor-critic finds a globally optimal pair of actor (policy) and critic (action-value function) at a linear rate of convergence. Our analysis may serve as a preliminary step towards a complete theoretical understanding of bilevel optimization with nonconvex subproblems, which is NP-hard in the worst case and is often solved using heuristics.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Bilevel OptimizationReinforcement Learning

Similar Papers 제목 키워드 기반

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…

On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost

2019-07-14 · Zhuoran Yang, Yongxin Chen, Mingyi Hong, Zhaoran Wang

Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization,…

Bilevel OptimizationReinforcement Learning

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

2019-11-11 · ICML 2020 1 · Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained vi…

Vocal Bursts Valence Prediction

Provably Convergent Actor-Critic for MARL through Risk-aversion

2026-02-12 · Yizhou Zhang, Eric Mazumdar arxiv

Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practic…

Multi-agent Reinforcement Learning

Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification

2022-06-07 · Gavin Zhang, Salar Fattahi, Richard Y. Zhang

We consider using gradient descent to minimize the nonconvex function $f(X)=\phi(XX^{T})$ over an $n\times r$ factor matrix $X$, in which $\phi$ is an underlying smooth convex cost function defined over $n\times n$ matri…