English
Related papers

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

200 papers

While the optimization landscape of policy gradient methods has been recently investigated for partially observed linear systems in terms of both static output feedback and dynamical controllers, they only provide convergence guarantees to…

Optimization and Control · Mathematics 2023-04-25 Feiran Zhao , Xingyun Fu , Keyou You

Robust control seeks stabilizing policies that perform reliably under adversarial disturbances, with $\mathcal{H}_\infty$ control as a classical formulation. It is known that policy optimization of robust $\mathcal{H}_\infty$ control…

Optimization and Control · Mathematics 2025-10-01 Yuto Watanabe , Feng-Yi Liao , Yang Zheng

We introduce the first direct policy search algorithm which provably converges to the globally optimal $\textit{dynamic}$ filter for the classical problem of predicting the outputs of a linear dynamical system, given noisy, partial…

Optimization and Control · Mathematics 2022-03-01 Jack Umenberger , Max Simchowitz , Juan C. Perdomo , Kaiqing Zhang , Russ Tedrake

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

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

This work revisits standard policy gradient methods used on restricted policy classes, which are known to get stuck in suboptimal critical points. We identify an important cause for this phenomenon to be that the policy gradient is itself…

Machine Learning · Computer Science 2026-05-12 Alex DeWeese , Guannan Qu

It is well known that both gradient descent and stochastic coordinate descent achieve a global convergence rate of $O(1/k)$ in the objective value, when applied to a scheme for minimizing a Lipschitz-continuously differentiable,…

Optimization and Control · Mathematics 2019-05-15 Ching-pei Lee , Stephen J. Wright

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Policy gradient methods usually rely on entropy regularization to prevent premature convergence. However, maximizing entropy indiscriminately pushes the policy towards a uniform distribution, often overriding the reward signal if not…

Machine Learning · Computer Science 2026-03-06 Luca Serfilippi , Giorgio Franceschelli , Antonio Corradi , Mirco Musolesi

Accelerated gradient methods are the cornerstones of large-scale, data-driven optimization problems that arise naturally in machine learning and other fields concerning data analysis. We introduce a gradient-based optimization framework for…

Optimization and Control · Mathematics 2022-03-22 Param Budhraja , Mayank Baranwal , Kunal Garg , Ashish Hota

We study a class of non-convex and non-smooth problems with \textit{rank} regularization to promote sparsity in optimal solution. We propose to apply the proximal gradient descent method to solve the problem and accelerate the process with…

Optimization and Control · Mathematics 2023-07-28 Mengyuan Zhang , Kai Liu

Solutions of optimization problems, including policy optimization in reinforcement learning, typically rely upon some variant of gradient descent. There has been much recent work in the machine learning, control, and optimization…

Machine Learning · Computer Science 2025-07-17 Eduardo D. Sontag

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$…

Machine Learning · Computer Science 2026-02-24 Zhenshuo Zhang , Minxuan Duan , Youran Ye , Hongyang R. Zhang

Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an…

Machine Learning · Computer Science 2019-03-26 Maryam Fazel , Rong Ge , Sham M. Kakade , Mehran Mesbahi

Many descent algorithms for multiobjective optimization have been developed in the last two decades. Tanabe et al. (Comput Optim Appl 72(2):339--361, 2019) proposed a proximal gradient method for multiobjective optimization, which can solve…

Optimization and Control · Mathematics 2022-04-11 Hiroki Tanabe , Ellen H. Fukuda , Nobuo Yamashita

In this paper, we derive a new linear convergence rate for the gradient method with fixed step lengths for non-convex smooth optimization problems satisfying the Polyak-Lojasiewicz (PL) inequality. We establish that the PL inequality is a…

Optimization and Control · Mathematics 2022-04-05 Hadi Abbaszadehpeivasti , Etienne de Klerk , Moslem Zamani

Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such "neural" policy gradient…

Machine Learning · Computer Science 2020-06-23 Lingxiao Wang , Qi Cai , Zhuoran Yang , Zhaoran Wang

Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe their success to the use of parameterized policies. However, while theoretical guarantees have been established for this class of algorithms, especially…

Machine Learning · Statistics 2024-02-14 Carlo Alfano , Rui Yuan , Patrick Rebeschini

We develop a rigorous framework for global non-convex optimization by reformulating the minimization problem as a discounted infinite-horizon optimal control problem. For non-convex, continuous, and possibly non-smooth objective functions…

Optimization and Control · Mathematics 2026-03-31 Yuyang Huang , Dante Kalise , Hicham Kouhkouh

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