English
Related papers

Related papers: Policy Gradient for Continuous-Time Mean-Field Con…

200 papers

With the outstanding performance of policy gradient (PG) method in the reinforcement learning field, the convergence theory of it has aroused more and more interest recently. Meanwhile, the significant importance and abundant theoretical…

Optimization and Control · Mathematics 2024-04-19 Xinpei Zhang , Guangyan Jia

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 have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by…

Machine Learning · Computer Science 2017-12-07 Peter Henderson , Thang Doan , Riashat Islam , David Meger

Model-free deep reinforcement learning (RL) methods have been successful in a wide variety of simulated domains. However, a major obstacle facing deep RL in the real world is their high sample complexity. Batch policy gradient methods offer…

Machine Learning · Computer Science 2017-03-01 Shixiang Gu , Timothy Lillicrap , Zoubin Ghahramani , Richard E. Turner , Sergey Levine

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient algorithms, the Natural Policy Gradient and the Gauss-Newton…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Bowen Song , Sebastien Gros , Andrea Iannelli

We consider the stochastic optimal control problem of McKean-Vlasov stochastic differential equation where the coefficients may depend upon the joint law of the state and control. By using feedback controls, we reformulate the problem into…

Probability · Mathematics 2017-03-09 Huyên Pham , Xiaoli Wei

In this paper, we present a novel method for computing the optimal feedback gain of the infinite-horizon Linear Quadratic Regulator (LQR) problem via an ordinary differential equation. We introduce a novel continuous-time Bellman error,…

Systems and Control · Electrical Eng. & Systems 2026-04-17 Armin Gießler , Albertus Johannes Malan , Sören Hohmann

For a general entropy-regularized time-inconsistent stochastic control problem, we propose a policy iteration algorithm (PIA) and establish its convergence to an equilibrium policy with an exponential convergence rate. The design of the PIA…

Optimization and Control · Mathematics 2026-03-27 Yu-Jui Huang , Xiang Yu , Keyu Zhang

We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an earlier work we introduced a policy iteration algorithm, where…

Optimization and Control · Mathematics 2020-05-05 Dimitri Bertsekas

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and…

Optimization and Control · Mathematics 2022-10-11 Bin Hu , Kaiqing Zhang , Na Li , Mehran Mesbahi , Maryam Fazel , Tamer Başar

Mean field games (MFGs) model interactions in large-population multi-agent systems through population distributions. Traditional learning methods for MFGs are based on fixed-point iteration (FPI), where policy updates and induced population…

Machine Learning · Computer Science 2025-02-17 Chenyu Zhang , Xu Chen , Xuan Di

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…

Many popular practical reinforcement learning (RL) algorithms employ evolving reward functions-through techniques such as reward shaping, entropy regularization, or curriculum learning-yet their theoretical foundations remain…

Machine Learning · Computer Science 2025-10-15 Rui Hu , Yu Chen , Longbo Huang

In this paper, we discuss the deterministic policy gradient using the Actor-Critic methods based on the linear compatible advantage function approximator, where the input spaces are continuous. When the policy is restricted by hard…

Systems and Control · Electrical Eng. & Systems 2021-04-07 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Sebastien Gros

The policy iteration method is a classical algorithm for solving optimal control problems. In this paper, we introduce a policy iteration method for Mean Field Games systems, and we study the convergence of this procedure to a solution of…

Analysis of PDEs · Mathematics 2021-07-12 Simone Cacace , Fabio Camilli , Alessandro Goffi

We formulate and compute a class of mean-field information dynamics for reaction-diffusion equations. Given a class of nonlinear reaction-diffusion equations and entropy type Lyapunov functionals, we study their gradient flows formulations…

Optimization and Control · Mathematics 2022-07-20 Wuchen Li , Wonjun Lee , Stanley Osher

The paper considers a forward-backward system of parabolic PDEs arising in a Mean Field Game (MFG) model where every agent controls the drift of a trajectory subject to Brownian diffusion, trying to escape a given bounded domain $\Omega$ in…

Analysis of PDEs · Mathematics 2022-12-23 Romain Ducasse , Guilherme Mazanti , Filippo Santambrogio

This paper is devoted to the numerical resolution of McKean-Vlasov control problems via the class of mean-field neural networks introduced in our companion paper [25] in order to learn the solution on the Wasserstein space. We propose…

Optimization and Control · Mathematics 2024-03-20 Huyên Pham , Xavier Warin

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

This paper studies a mean field game inspired by crowd motion in which agents evolve in a compact domain and want to reach its boundary minimizing the sum of their travel time and a given boundary cost. Interactions between agents occur…

Optimization and Control · Mathematics 2020-01-31 Samer Dweik , Guilherme Mazanti