English
Related papers

Related papers: Mirror descent actor-critic methods for entropy re…

200 papers

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

Policy mirror descent (PMD) is a general policy optimization framework in reinforcement learning, which can cover a wide range of typical policy optimization methods by specifying different mirror maps. Existing analysis of PMD requires…

Optimization and Control · Mathematics 2025-09-24 Jiacai Liu , Wenye Li , Ke Wei

We show that the simplest actor-critic method -- a linear softmax policy updated with TD through interaction with a linear MDP, but featuring no explicit regularization or exploration -- does not merely find an optimal policy, but moreover…

Machine Learning · Computer Science 2022-03-15 Yuzheng Hu , Ziwei Ji , Matus Telgarsky

In this paper, we present a probability one convergence proof, under suitable conditions, of a certain class of actor-critic algorithms for finding approximate solutions to entropy-regularized MDPs using the machinery of stochastic…

Machine Learning · Computer Science 2019-10-23 Wesley Suttle , Zhuoran Yang , Kaiqing Zhang , Ji Liu

Mirror descent (MD), a well-known first-order method in constrained convex optimization, has recently been shown as an important tool to analyze trust-region algorithms in reinforcement learning (RL). However, there remains a considerable…

Machine Learning · Computer Science 2021-06-08 Manan Tomar , Lior Shani , Yonathan Efroni , Mohammad Ghavamzadeh

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

It is well known that mirror descent may diverge or cycle on merely monotone variational inequalities. In this paper, we propose \emph{Target Mirror Descent} (TMD), a unified framework that stabilizes monotone flows via a target point…

Optimization and Control · Mathematics 2026-04-22 Yu-Wen Chen , Can Kizilkale , Murat Arcak

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

Regularization is a core component of recent Reinforcement Learning (RL) algorithms. Mirror Descent Value Iteration (MDVI) uses both Kullback-Leibler divergence and entropy as regularizers in its value and policy updates. Despite its…

Machine Learning · Computer Science 2026-01-09 Ryo Iwaki

Actor-critic methods can achieve incredible performance on difficult reinforcement learning problems, but they are also prone to instability. This is partly due to the interaction between the actor and critic during learning, e.g., an…

Machine Learning · Computer Science 2019-02-26 Simone Parisi , Voot Tangkaratt , Jan Peters , Mohammad Emtiyaz Khan

Policy Mirror Descent (PMD) has emerged as a unifying framework in reinforcement learning (RL) by linking policy gradient methods with a first-order optimization method known as mirror descent. At its core, PMD incorporates two key…

Machine Learning · Computer Science 2025-07-14 Jan Felix Kleuker , Aske Plaat , Thomas Moerland

We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space. The flow is a continuous-time analogue of a policy mirror descent…

Optimization and Control · Mathematics 2025-06-09 Bekzhan Kerimkulov , James-Michael Leahy , David Siska , Lukasz Szpruch , Yufei Zhang

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized…

Machine Learning · Computer Science 2025-06-24 Hwanwoo Kim , Panos Toulis , Eric Laber

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

We propose a new policy gradient method, named homotopic policy mirror descent (HPMD), for solving discounted, infinite horizon MDPs with finite state and action spaces. HPMD performs a mirror descent type policy update with an additional…

Machine Learning · Computer Science 2022-11-30 Yan Li , Guanghui Lan , Tuo Zhao

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

This paper focuses on applying entropic mirror descent to solve linear systems, where the main challenge for the convergence analysis stems from the unboundedness of the domain. To overcome this without imposing restrictive assumptions, we…

Optimization and Control · Mathematics 2026-03-09 Yura Malitsky , Alexander Posch

We analyze the global convergence of the single-timescale actor-critic (AC) algorithm for the infinite-horizon discounted Markov Decision Processes (MDPs) with finite state spaces. To this end, we introduce an elegant analytical framework…

Machine Learning · Computer Science 2025-06-05 Navdeep Kumar , Priyank Agrawal , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

Mirror descent (MD) is a powerful first-order optimization technique that subsumes several optimization algorithms including gradient descent (GD). In this work, we develop a semi-definite programming (SDP) framework to analyze the…

Optimization and Control · Mathematics 2022-01-19 Youbang Sun , Mahyar Fazlyab , Shahin Shahrampour

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
‹ Prev 1 2 3 10 Next ›