English
Related papers

Related papers: Landscape of Policy Optimization for Finite Horizo…

200 papers

We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation…

Optimization and Control · Mathematics 2024-01-18 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Alejandro Ribeiro

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

Machine Learning · Computer Science 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots…

Optimization and Control · Mathematics 2025-04-30 René Carmona , Mathieu Laurière , Zongjun Tan

We propose a stochastic gradient framework for solving stochastic composite convex optimization problems with (possibly) infinite number of linear inclusion constraints that need to be satisfied almost surely. We use smoothing and homotopy…

Optimization and Control · Mathematics 2019-02-04 Olivier Fercoq , Ahmet Alacaoglu , Ion Necoara , Volkan Cevher

We consider a stochastic inventory control problem under censored demands, lost sales, and positive lead times. This is a fundamental problem in inventory management, with significant literature establishing near-optimality of a simple…

Machine Learning · Computer Science 2019-05-14 Shipra Agrawal , Randy Jia

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

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

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…

We study offline Reinforcement Learning in large infinite-horizon discounted Markov Decision Processes (MDPs) when the reward and transition models are linearly realizable under a known feature map. Starting from the classic linear-program…

Machine Learning · Computer Science 2024-05-24 Gergely Neu , Nneka Okolo

Gradient-based approaches to direct policy search in reinforcement learning have received much recent attention as a means to solve problems of partial observability and to avoid some of the problems associated with policy degradation in…

Artificial Intelligence · Computer Science 2019-11-18 Jonathan Baxter , Peter L. Bartlett

Decision-making problems in uncertain or stochastic domains are often formulated as Markov decision processes (MDPs). Policy iteration (PI) is a popular algorithm for searching over policy-space, the size of which is exponential in the…

Artificial Intelligence · Computer Science 2013-01-30 Yishay Mansour , Satinder Singh

The goal of reinforcement learning is estimating a policy that maps states to actions and maximizes the cumulative reward of a Markov Decision Process (MDP). This is oftentimes achieved by estimating first the optimal (reward) value…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

Multi-agent interactions are increasingly important in the context of reinforcement learning, and the theoretical foundations of policy gradient methods have attracted surging research interest. We investigate the global convergence of…

Optimization and Control · Mathematics 2023-03-21 Sarath Pattathil , Kaiqing Zhang , Asuman Ozdaglar

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

Minimization of a smooth function on a sphere or, more generally, on a smooth manifold, is the simplest non-convex optimization problem. It has a lot of applications. Our goal is to propose a version of the gradient projection algorithm for…

Optimization and Control · Mathematics 2019-06-28 Maxim Balashov , Boris Polyak , Andrey Tremba

To overcome the curses of dimensionality and modeling of Dynamic Programming (DP) methods to solve Markov Decision Process (MDP) problems, Reinforcement Learning (RL) methods are adopted in practice. Contrary to traditional RL algorithms…

Machine Learning · Computer Science 2021-08-24 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

Sufficient conditions are identified under which the value function and the optimal strategy of a Markov decision process (MDP) are even and quasi-convex in the state. The key idea behind these conditions is the following. First, sufficient…

Optimization and Control · Mathematics 2017-09-12 Jhelum Chakravorty , Aditya Mahajan

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

We present a hybrid systems framework for distributed multi-agent optimization in which agents execute computations in continuous time and communicate in discrete time. The optimization algorithm is analogous to a continuous-time form of…

Optimization and Control · Mathematics 2026-03-17 Katherine R. Hendrickson , Dawn M. Hustig-Schultz , Matthew T. Hale , Ricardo G. Sanfelice

Partially Observable Markov Decision Processes (POMDPs) provide an efficient way to model real-world sequential decision making processes. Motivated by the problem of maintenance and inspection of a group of infrastructure components with…

Optimization and Control · Mathematics 2024-08-15 Manav Vora , Pranay Thangeda , Michael N. Grussing , Melkior Ornik