English
Related papers

Related papers: A Fisher-Rao gradient flow for entropy-regularised…

200 papers

Entropy regularization has been widely used in policy optimization algorithms to enhance exploration and the robustness of the optimal control; however it also introduces an additional regularization bias. This work quantifies the impact of…

Optimization and Control · Mathematics 2025-03-25 Deven Sethi , David Šiška , Yufei Zhang

We study the global convergence of policy gradient for infinite-horizon, continuous state and action space, and entropy-regularized Markov decision processes (MDPs). We consider a softmax policy with (one-hidden layer) neural network…

Optimization and Control · Mathematics 2022-06-17 Bekzhan Kerimkulov , James-Michael Leahy , David Šiška , Lukasz Szpruch

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation…

Optimization and Control · Mathematics 2025-10-17 Denis Zorba , David Šiška , Lukasz Szpruch

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

We consider infinite-horizon discounted Markov decision problems with finite state and action spaces and study the convergence rates of the projected policy gradient method and a general class of policy mirror descent methods, all with…

Optimization and Control · Mathematics 2022-03-08 Lin Xiao

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function…

Machine Learning · Computer Science 2026-05-26 Ziyue Chen , David Šiška , Lukasz Szpruch

Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient method based on the Fisher information matrix of the…

Optimization and Control · Mathematics 2025-02-05 Johannes Müller , Semih Çaycı , Guido Montúfar

We study the error introduced by entropy regularization in infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength, both in a weighted…

Optimization and Control · Mathematics 2025-12-16 Johannes Müller , Semih Cayci

We develop a generic policy gradient method with the global optimality guarantee for robust Markov Decision Processes (MDPs). While policy gradient methods are widely used for solving dynamic decision problems due to their scalable and…

Machine Learning · Computer Science 2024-11-01 Qiuhao Wang , Shaohang Xu , Chin Pang Ho , Marek Petrik

We consider policy gradient methods for stochastic optimal control problem in continuous time. In particular, we analyze the gradient flow for the control, viewed as a continuous time limit of the policy gradient method. We prove the global…

Optimization and Control · Mathematics 2025-04-15 Mo Zhou , Jianfeng Lu

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

Machine Learning · Computer Science 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez

We make three contributions toward better understanding policy gradient methods in the tabular setting. First, we show that with the true gradient, policy gradient with a softmax parametrization converges at a $O(1/t)$ rate, with constants…

Machine Learning · Computer Science 2022-06-03 Jincheng Mei , Chenjun Xiao , Csaba Szepesvari , Dale Schuurmans

We address the problem of finding the optimal policy of a constrained Markov decision process (CMDP) using a gradient descent-based algorithm. Previous results have shown that a primal-dual approach can achieve an $\mathcal{O}(1/\sqrt{T})$…

Machine Learning · Computer Science 2022-02-07 Tao Liu , Ruida Zhou , Dileep Kalathil , P. R. Kumar , Chao Tian

Policy gradient algorithms have been widely applied to Markov decision processes and reinforcement learning problems in recent years. Regularization with various entropy functions is often used to encourage exploration and improve…

Machine Learning · Computer Science 2023-06-09 Haoya Li , Samarth Gupta , Hsiangfu Yu , Lexing Ying , Inderjit Dhillon

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

Optimization and Control · Mathematics 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao

We consider a class of optimization problems on the space of probability measures motivated by the mean-field approach to studying neural networks. Such problems can be solved by constructing continuous-time gradient flows that converge to…

Optimization and Control · Mathematics 2026-02-18 Petra Lazić , Linshan Liu , Mateusz B. Majka

Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the…

Machine Learning · Computer Science 2026-05-22 David Šiška , Yufei Zhang

We study the convergence of several natural policy gradient (NPG) methods in infinite-horizon discounted Markov decision processes with regular policy parametrizations. For a variety of NPGs and reward functions we show that the…

Optimization and Control · Mathematics 2024-02-21 Johannes Müller , Guido Montúfar

We provide theoretical guarantees for convergence of discrete-time policy mirror descent with inexact advantage functions updated using temporal difference (TD) learning for entropy regularised MDPs in Polish state and action spaces. We…

Optimization and Control · Mathematics 2026-02-12 Denis Zorba , David Šiška , Lukasz Szpruch

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang
‹ Prev 1 2 3 10 Next ›