English
Related papers

Related papers: Non-asymptotic Convergence Analysis of Two Time-sc…

200 papers

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…

Machine Learning · Computer Science 2019-07-16 Zhuoran Yang , Yongxin Chen , Mingyi Hong , Zhaoran Wang

Asynchronous and parallel implementation of standard reinforcement learning (RL) algorithms is a key enabler of the tremendous success of modern RL. Among many asynchronous RL algorithms, arguably the most popular and effective one is the…

Machine Learning · Computer Science 2023-08-02 Han Shen , Kaiqing Zhang , Mingyi Hong , Tianyi Chen

Natural actor-critic (NAC) and its variants, equipped with the representation power of neural networks, have demonstrated impressive empirical success in solving Markov decision problems with large state spaces. In this paper, we present a…

Machine Learning · Computer Science 2022-06-03 Semih Cayci , Niao He , R. Srikant

We establish an optimal sample complexity of $O(\epsilon^{-2})$ for obtaining an $\epsilon$-optimal global policy using a single-timescale actor-critic (AC) algorithm in infinite-horizon discounted Markov decision processes (MDPs) with…

Machine Learning · Computer Science 2026-05-08 Navdeep Kumar , Tehila Dahan , Lior Cohen , Ananyabrata Barua , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

In this paper, we establish last-iterate convergence rates for off-policy actor--critic methods in reinforcement learning. In particular, under a single-loop, single-timescale implementation and a broad class of policy updates, including…

Machine Learning · Computer Science 2026-05-14 Ishaq Hamza , Zaiwei Chen

Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years. However, most of the existing theoretical support for AC algorithms focuses on the case of linear function approximations,…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Siyu Chen , Zhuoran Yang , Michael I. Jordan , Zhaoran Wang

Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their generality, good convergence properties, and possible biological…

Machine Learning · Computer Science 2009-09-17 D. Di Castro , R. Meir

In this paper, we provide finite-sample convergence guarantees for an off-policy variant of the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we show that the algorithm converges to a global optimal…

Machine Learning · Computer Science 2021-06-14 Sajad Khodadadian , Zaiwei Chen , Siva Theja Maguluri

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 updates, we focus on…

Machine Learning · Computer Science 2021-06-15 Zuyue Fu , Zhuoran Yang , Zhaoran Wang

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 largely missing in…

Machine Learning · Computer Science 2022-02-24 Anas Barakat , Pascal Bianchi , Julien Lehmann

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

Machine Learning · Computer Science 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work…

Machine Learning · Statistics 2025-05-07 Kevin Tan , Wei Fan , Yuting Wei

By using an parametric value function to replace the Monte-Carlo rollouts for value estimation, the actor-critic (AC) algorithms can reduce the variance of stochastic policy gradient so that to improve the convergence rate. While existing…

Machine Learning · Computer Science 2024-08-19 Yanjie Dong , Haijun Zhang , Gang Wang , Shisheng Cui , Xiping Hu

As an important algorithm in deep reinforcement learning, advantage actor critic (A2C) has been widely succeeded in both discrete and continuous control tasks with raw pixel inputs, but its sample efficiency still needs to improve more. In…

Machine Learning · Computer Science 2022-02-15 Yuan Wang , Chunyuan Zhang , Tianzong Yu , Meng Ma

Actor-critic algorithms are widely used in reinforcement learning, but are challenging to mathematically analyse due to the online arrival of non-i.i.d. data samples. The distribution of the data samples dynamically changes as the model is…

Machine Learning · Computer Science 2023-09-20 Ziheng Wang , Justin Sirignano

In cooperative stochastic games multiple agents work towards learning joint optimal actions in an unknown environment to achieve a common goal. In many real-world applications, however, constraints are often imposed on the actions that can…

Multiagent Systems · Computer Science 2020-07-14 Raghuram Bharadwaj Diddigi , Sai Koti Reddy Danda , Prabuchandran K. J. , Shalabh Bhatnagar

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 via Gradient Emphasis…

Machine Learning · Computer Science 2020-11-25 Shangtong Zhang , Bo Liu , Hengshuai Yao , Shimon Whiteson

Two timescale stochastic approximation (SA) has been widely used in value-based reinforcement learning algorithms. In the policy evaluation setting, it can model the linear and nonlinear temporal difference learning with gradient correction…

Machine Learning · Computer Science 2020-11-11 Tengyu Xu , Yingbin Liang

The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures…

Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this approach comes at the expense of training instability, caused…

Machine Learning · Computer Science 2024-06-11 Bahareh Tasdighi , Abdullah Akgül , Manuel Haussmann , Kenny Kazimirzak Brink , Melih Kandemir