English
Related papers

Related papers: Value Approximation for Two-Player General-Sum Dif…

200 papers

Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs (HJI) PDEs. Self-supervised learning has been used to approximate solutions of such PDEs while circumventing the curse of…

Machine Learning · Computer Science 2023-02-28 Lei Zhang , Mukesh Ghimire , Wenlong Zhang , Zhe Xu , Yi Ren

General-sum differential games can approximate values solved by Hamilton-Jacobi-Isaacs (HJI) equations for efficient inference when information is incomplete. However, solving such games through conventional methods encounters the curse of…

Robotics · Computer Science 2025-03-11 Lei Zhang , Mukesh Ghimire , Wenlong Zhang , Zhe Xu , Yi Ren

The values of two-player general-sum differential games are viscosity solutions to Hamilton-Jacobi-Isaacs (HJI) equations. Value and policy approximations for such games suffer from the curse of dimensionality (CoD). Alleviating CoD through…

Machine Learning · Computer Science 2024-06-04 Lei Zhang , Mukesh Ghimire , Zhe Xu , Wenlong Zhang , Yi Ren

Hamilton-Jacobi-Isaacs (HJI) PDEs are the governing equations for the two-player general-sum games. Unlike Reinforcement Learning (RL) methods, which are data-intensive methods for learning value function, learning HJ PDEs provide a…

Multiagent Systems · Computer Science 2023-11-06 Mukesh Ghimire , Lei Zhang , Wenlong Zhang , Yi Ren , Zhe Xu

We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to solve high-dimensional, nonconvex Hamilton--Jacobi--Isaacs (HJI) equations arising in stochastic…

Numerical Analysis · Mathematics 2025-07-24 Hee Jun Yang , Minjung Gim , Yeoneung Kim

We propose a physics-informed neural networks (PINNs) framework to solve the infinite-horizon optimal control problem of nonlinear systems. In particular, since PINNs are generally able to solve a class of partial differential equations…

Systems and Control · Electrical Eng. & Systems 2025-05-29 Filippos Fotiadis , Kyriakos G. Vamvoudakis

This paper presents Hamilton-Jacobi (HJ) formulations for two classes of two-player zero-sum games: one with a maximum cost value over time, and one with a minimum cost value over time. In the zero-sum game setting, player A minimizes the…

Optimization and Control · Mathematics 2021-06-30 Donggun Lee , Claire J. Tomlin

In this work, we study physics-informed neural networks (PINNs) constrained by partial differential equations (PDEs) and their application in approximating PDEs with two characteristic scales. From a continuous perspective, our formulation…

Optimization and Control · Mathematics 2024-09-06 Michael Hintermüller , Denis Korolev

We consider the problem of learning Nash equilibrial policies for two-player risk-sensitive collision-avoiding interactions. Solving the Hamilton-Jacobi-Isaacs equations of such general-sum differential games in real time is an open…

Robotics · Computer Science 2025-03-21 Lei Zhang , Siddharth Das , Tanner Merry , Wenlong Zhang , Yi Ren

Physics-informed neural networks (PINNs) have recently emerged as a prominent paradigm for solving partial differential equations (PDEs), yet their training strategies remain underexplored. While hard prioritization methods inspired by…

Machine Learning · Computer Science 2025-12-22 Zhaoqian Gao , Min Yanga

This paper develops an algorithm for upper- and lower-bounding the value function for a class of linear time-varying games subject to convex control sets. In particular, a two-player zero-sum differential game is considered where the…

Optimization and Control · Mathematics 2025-03-12 Vincent Liu , Chris Manzie , Peter M. Dower

Hamilton-Jacobi (HJ) partial differential equations (PDEs) have diverse applications spanning physics, optimal control, game theory, and imaging sciences. This research introduces a first-order optimization-based technique for HJ PDEs,…

Numerical Analysis · Mathematics 2023-10-04 Tingwei Meng , Wenbo Hao , Siting Liu , Stanley J. Osher , Wuchen Li

In this paper, we develop algorithms to overcome the curse of dimensionality in possibly non-convex state-dependent Hamilton-Jacobi equations (HJ PDEs) arising from optimal control and differential game problems. The subproblems are…

Optimization and Control · Mathematics 2018-02-19 Yat Tin Chow , Jerome Darbon , Stanley Osher , Wotao Yin

The curse-of-dimensionality taxes computational resources heavily with exponentially increasing computational cost as the dimension increases. This poses great challenges in solving high-dimensional PDEs, as Richard E. Bellman first pointed…

Machine Learning · Computer Science 2024-05-20 Zheyuan Hu , Khemraj Shukla , George Em Karniadakis , Kenji Kawaguchi

It is well known that time dependent Hamilton-Jacobi-Isaacs partial differential equations (HJ PDE), play an important role in analyzing continuous dynamic games and control theory problems. An important tool for such problems when they…

Optimization and Control · Mathematics 2016-05-09 Jérôme Darbon , Stanley Osher

The majority of methods used to compute approximations to the Hamilton-Jacobi-Isaacs partial differential equation (HJI PDE) rely on the discretization of the state space to perform dynamic programming updates. This type of approach is…

Machine Learning · Computer Science 2019-04-15 Vicenç Rubies-Royo , Claire Tomlin

We propose a physics-informed neural network policy iteration (PINN-PI) framework for solving stochastic optimal control problems governed by second-order Hamilton--Jacobi--Bellman (HJB) equations. At each iteration, a neural network is…

Machine Learning · Computer Science 2025-08-05 Yeongjong Kim , Yeoneung Kim , Minseok Kim , Namkyeong Cho

In this work, we present a hybrid numerical method for solving evolution partial differential equations (PDEs) by merging the time finite element method with deep neural networks. In contrast to the conventional deep learning-based…

Numerical Analysis · Mathematics 2024-09-05 Xiaodong Feng , Haojiong Shangguan , Tao Tang , Xiaoliang Wan , Tao Zhou

We develop a game-theoretic framework for adversarially robust optimal safe predefined-time stabilization of parameter-dependent nonlinear dynamical systems with nonquadratic cost functionals. Our approach ensures that all system…

Optimization and Control · Mathematics 2025-11-20 Nick-Marios T. Kokolakis , Shanqing Liu , Jerome Darbon , Rahul Mangharam , George Em Karniadakis

Optimal control problems are crucial in various domains, including path planning, robotics, and humanoid control, demonstrating their broad applicability. The connection between optimal control and Hamilton-Jacobi (HJ) partial differential…

Optimization and Control · Mathematics 2024-03-06 Tingwei Meng , Siting Liu , Wuchen Li , Stanley Osher
‹ Prev 1 2 3 10 Next ›