English
Related papers

Related papers: Two-Timescale Critic-Actor for Average Reward MDPs…

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

We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-03-10 Anirudh Satheesh , Pankaj Kumar Barman , Washim Uddin Mondal , Vaneet Aggarwal

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points…

Machine Learning · Computer Science 2026-05-15 Sanjeev Manivannan , Shuban V

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

Machine Learning · Computer Science 2025-05-07 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

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

We investigate the discounting mismatch in actor-critic algorithm implementations from a representation learning perspective. Theoretically, actor-critic algorithms usually have discounting for both actor and critic, i.e., there is a…

Machine Learning · Computer Science 2022-01-27 Shangtong Zhang , Romain Laroche , Harm van Seijen , Shimon Whiteson , Remi Tachet des Combes

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

This paper proposes a new actor-critic-style algorithm called Dual Actor-Critic or Dual-AC. It is derived in a principled way from the Lagrangian dual form of the Bellman optimality equation, which can be viewed as a two-player game between…

Machine Learning · Computer Science 2018-01-01 Bo Dai , Albert Shaw , Niao He , Lihong Li , Le Song

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.…

Optimization and Control · Mathematics 2024-11-21 Sihan Zeng , Thinh T. Doan , Justin Romberg

Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in…

Machine Learning · Statistics 2019-10-29 Kamil Ciosek , Quan Vuong , Robert Loftin , Katja Hofmann

We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…

Optimization and Control · Mathematics 2025-01-27 Mo Zhou , Jianfeng Lu

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for…

Machine Learning · Computer Science 2018-10-16 Ilya Kostrikov , Kumar Krishna Agrawal , Debidatta Dwibedi , Sergey Levine , Jonathan Tompson

The first aim of this paper is to establish the weak convergence rate of nonlinear two-time-scale stochastic approximation algorithms. Its second aim is to introduce the averaging principle in the context of two-time-scale stochastic…

Probability · Mathematics 2007-05-23 Abdelkader Mokkadem , Mariane Pelletier

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for…

Machine Learning · Computer Science 2025-09-09 Gaspard Lambrechts , Damien Ernst , Aditya Mahajan

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 analyzing…

Machine Learning · Computer Science 2024-01-29 Xuyang Chen , Lin Zhao

Actor-critic algorithms have shown remarkable success in solving state-of-the-art decision-making problems. However, despite their empirical effectiveness, their theoretical underpinnings remain relatively unexplored, especially with neural…

Machine Learning · Computer Science 2023-06-21 Mudit Gaur , Amrit Singh Bedi , Di Wang , Vaneet Aggarwal

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

The actor-critic (AC) algorithm is a popular method to find an optimal policy in reinforcement learning. In the infinite horizon scenario, the finite-sample convergence rate for the AC and natural actor-critic (NAC) algorithms has been…

Machine Learning · Computer Science 2021-02-15 Tengyu Xu , Zhe Wang , Yingbin Liang

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

Machine Learning · Computer Science 2023-01-31 Harshat Kumar , Alec Koppel , Alejandro Ribeiro