English
Related papers

Related papers: Stochastic Policy Gradient Methods: Improved Sampl…

200 papers

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 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

Motivated by applications arising from sensor networks and machine learning, we consider the problem of minimizing a finite sum of nondifferentiable convex functions where each component function is associated with an agent and a…

Optimization and Control · Mathematics 2021-03-22 Harshal D. Kaushik , Farzad Yousefian

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous works for convex optimization, either the convergence is only…

Optimization and Control · Mathematics 2023-03-01 Zijian Liu , Ta Duy Nguyen , Thien Hang Nguyen , Alina Ene , Huy Lê Nguyen

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 focus on analyzing the classical stochastic projected gradient methods under a general dependent data sampling scheme for constrained smooth nonconvex optimization. We show the worst-case rate of convergence $\tilde{O}(t^{-1/4})$ and…

Optimization and Control · Mathematics 2023-06-26 Ahmet Alacaoglu , Hanbaek Lyu

Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a discrete set of actions…

Machine Learning · Computer Science 2019-02-19 Carson Eisenach , Haichuan Yang , Ji Liu , Han Liu

Gradient-based algorithms are one of the methods of choice for the optimisation of Markov Decision Processes. In this article we will present a novel approximate Newton algorithm for the optimisation of such models. The algorithm has…

Optimization and Control · Mathematics 2015-08-05 Thomas Furmston , David Barber

In this work, we develop new optimization algorithms that use approximate second-order information combined with the gradient regularization technique to achieve fast global convergence rates for both convex and non-convex objectives. The…

Optimization and Control · Mathematics 2025-06-17 Andrei Semenov , Martin Jaggi , Nikita Doikov

Motivated by penalized likelihood maximization in complex models, we study optimization problems where neither the function to optimize nor its gradient have an explicit expression, but its gradient can be approximated by a Monte Carlo…

Computation · Statistics 2017-09-28 Gersende Fort , Edouard Ollier , Adeline Samson

Stochastic gradient descent (SGD) is a powerful optimization technique that is particularly useful in online learning scenarios. Its convergence analysis is relatively well understood under the assumption that the data samples are…

Machine Learning · Computer Science 2024-10-03 Ethan Che , Jing Dong , Xin T. Tong

Optimal transport (OT) defines a powerful framework to compare probability distributions in a geometrically faithful way. However, the practical impact of OT is still limited because of its computational burden. We propose a new class of…

Optimization and Control · Mathematics 2016-05-30 Genevay Aude , Marco Cuturi , Gabriel Peyré , Francis Bach

Reliable path planning in stochastic transportation networks requires decisions that account for uncertain and correlated travel times on irregular road graphs, rather than only minimizing expected delay. Such networks exhibit strong…

Machine Learning · Computer Science 2026-05-18 Xing Wei , Yuanhang Wang , Duoxiang Zhao , Zezhou Zhang , Hao Qin , Yuqi Ouyang

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement…

Machine Learning · Computer Science 2019-12-30 Devesh Jha , Arvind Raghunathan , Diego Romeres

We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to…

Optimization and Control · Mathematics 2019-05-16 Quoc Tran-Dinh , Nhan H. Pham , Dzung T. Phan , Lam M. Nguyen

We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with…

Machine Learning · Computer Science 2020-10-20 Dongruo Zhou , Pan Xu , Quanquan Gu

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Machine Learning · Computer Science 2025-06-09 Alessandro Montenegro , Leonardo Cesani , Marco Mussi , Matteo Papini , Alberto Maria Metelli

We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. Although many algorithms have been proposed for contextual bandit, most of them rely on…

Machine Learning · Computer Science 2021-06-08 Qin Ding , Cho-Jui Hsieh , James Sharpnack