English
Related papers

Related papers: On the Global Convergence Rates of Softmax Policy …

200 papers

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do…

Machine Learning · Computer Science 2020-03-02 Chris Nota , Philip S. Thomas

The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Pierre-Luc Bacon , Doina Precup

We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon…

Optimization and Control · Mathematics 2025-10-16 Dongsheng Ding , Kaiqing Zhang , Jiali Duan , Tamer Başar , Mihailo R. Jovanović

This work establishes new convergence guarantees for gradient descent in smooth convex optimization via a computer-assisted analysis technique. Our theory allows nonconstant stepsize policies with frequent long steps potentially violating…

Optimization and Control · Mathematics 2024-02-06 Benjamin Grimmer

We consider stochastic gradient descent algorithms for minimizing a non-smooth, strongly-convex function. Several forms of this algorithm, including suffix averaging, are known to achieve the optimal $O(1/T)$ convergence rate in…

Machine Learning · Computer Science 2019-09-04 Nicholas J. A. Harvey , Christopher Liaw , Sikander Randhawa

In this effort, we consider the impact of regularization on the diversity of actions taken by policies generated from reinforcement learning agents trained using a policy gradient. Policy gradient agents are prone to entropy collapse, which…

Machine Learning · Computer Science 2023-10-10 Andrew Starnes , Anton Dereventsov , Clayton Webster

This work explores generalizations of the Polyak-Lojasiewicz inequality (PLI) and their implications for the convergence behavior of gradient flows in optimization problems. Motivated by the continuous-time linear quadratic regulator…

Optimization and Control · Mathematics 2025-04-01 Arthur Castello B. de Oliveira , Leilei Cui , Eduardo D. Sontag

Recently Grimmer [1] showed for smooth convex optimization by utilizing longer steps periodically, gradient descent's textbook $LD^2/2T$ convergence guarantees can be improved by constant factors, conjecturing an accelerated rate strictly…

Optimization and Control · Mathematics 2023-09-28 Benjamin Grimmer , Kevin Shu , Alex L. Wang

Policy gradient methods are one of the most successful approaches for solving challenging reinforcement learning problems. Despite their empirical successes, many state-of-the-art policy gradient algorithms for discounted problems deviate…

Machine Learning · Computer Science 2026-04-02 Weizhen Wang , Jianping He , Xiaoming Duan

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

Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work explores reinforcement learning methods for finding the optimal…

Machine Learning · Computer Science 2025-04-11 Yinbin Han , Meisam Razaviyayn , Renyuan Xu

Policy-gradient methods are widely used for learning control policies. They can be easily distributed to multiple workers and reach state-of-the-art results in many domains. Unfortunately, they exhibit large variance and subsequently suffer…

Machine Learning · Computer Science 2022-09-29 Gal Dalal , Assaf Hallak , Shie Mannor , Gal Chechik

Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and…

Optimization and Control · Mathematics 2023-10-10 Shicong Cen , Yuejie Chi

Approaches to policy optimization have been motivated from diverse principles, based on how the parametric model is interpreted (e.g. value versus policy representation) or how the learning objective is formulated, yet they share a common…

Machine Learning · Computer Science 2022-06-20 Ramki Gummadi , Saurabh Kumar , Junfeng Wen , Dale Schuurmans

The {\L}ojasiewicz inequality characterizes objective-value convergence along gradient flows and, in special cases, yields exponential decay of the cost. However, such results do not directly give rates of convergence in the state. In this…

Optimization and Control · Mathematics 2026-03-30 Andreas Oliveira , Arthur C. B. de Oliveira , Mario Sznaier , Eduardo Sontag

Softmax policy gradient converges at $O(1/t)$, but its transient behavior near sub-optimal corners of the simplex can be exponentially slow. The bottleneck is self-trapping: negative-advantage actions reinforce the corner policy and can…

Machine Learning · Computer Science 2026-05-13 Jincheng Mei , Ian Osband

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Machine Learning · Computer Science 2022-05-17 Yue Wang , Shaofeng Zou

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim…

Machine Learning · Computer Science 2019-06-11 Zafarali Ahmed , Nicolas Le Roux , Mohammad Norouzi , Dale Schuurmans