English
Related papers

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

200 papers

In this paper, we consider state and control path-dependent stochastic zero-sum differential games, where the dynamics and the running cost include both state and control paths of the players. Using the notion of nonanticipative strategies,…

Optimization and Control · Mathematics 2021-02-10 Jun Moon

This paper develops a novel deep learning approach for solving evolutionary equations, which integrates sequential learning strategies with an enhanced hard constraint strategy featuring trainable parameters, addressing the low…

Machine Learning · Computer Science 2025-03-25 Yushi Zhang , Shuai Su , Yong Wang , Yanzhong Yao

This paper addresses a continuous-time risk-minimizing two-player zero-sum stochastic differential game (SDG), in which each player aims to minimize its probability of failure. Failure occurs in the event when the state of the game enters…

Optimization and Control · Mathematics 2023-08-23 Apurva Patil , Yujing Zhou , David Fridovich-Keil , Takashi Tanaka

For artificially intelligent learning systems to have widespread applicability in real-world settings, it is important that they be able to operate decentrally. Unfortunately, decentralized control is difficult -- computing even an…

Artificial Intelligence · Computer Science 2021-01-13 Samuel Sokota , Edward Lockhart , Finbarr Timbers , Elnaz Davoodi , Ryan D'Orazio , Neil Burch , Martin Schmid , Michael Bowling , Marc Lanctot

In this paper, numerical methods using Physics-Informed Neural Networks (PINNs) are presented with the aim to solve higher-order ordinary differential equations (ODEs). Indeed, this deep-learning technique is successfully applied for…

Computational Physics · Physics 2023-07-17 Hubert Baty

This paper develops a hierarchical games-in-games control architecture for hybrid stochastic systems governed by regime-switching jump-diffusions. We model the interplay between continuous state dynamics and discrete mode transitions as a…

Systems and Control · Electrical Eng. & Systems 2025-12-23 Yunian Pan , Quanyan Zhu

Hamilton-Jacobi (HJ) reachability analysis is a widely adopted verification tool to provide safety and performance guarantees for autonomous systems. However, it involves solving a partial differential equation (PDE) to compute a safety…

Robotics · Computer Science 2025-05-12 Aditya Singh , Zeyuan Feng , Somil Bansal

Physics-informed neural networks (PINNs) have been proposed to learn the solution of partial differential equations (PDE). In PINNs, the residual form of the PDE of interest and its boundary conditions are lumped into a composite objective…

Computational Physics · Physics 2022-05-24 Shamsulhaq Basir , Inanc Senocak

Physics-informed Neural Networks (PINNs) have recently achieved remarkable progress in solving Partial Differential Equations (PDEs) in various fields by minimizing a weighted sum of PDE loss and boundary loss. However, there are several…

Machine Learning · Computer Science 2023-06-06 Jiachen Yao , Chang Su , Zhongkai Hao , Songming Liu , Hang Su , Jun Zhu

We study a two-player zero-sum stochastic differential game with both players adopting impulse controls, on a finite time horizon. The Hamilton-Jacobi-Bellman-Isaacs (HJBI) partial differential equation of the game turns out to be a…

Probability · Mathematics 2012-06-26 Andrea Cosso

Hamilton-Jacobi (HJ) Reachability offers a framework for generating safe value functions and policies in the face of adversarial disturbance, but is limited by the curse of dimensionality. Physics-informed deep learning is able to overcome…

Robotics · Computer Science 2025-10-22 Ryan Teoh , Sander Tonkens , William Sharpless , Aijia Yang , Zeyuan Feng , Somil Bansal , Sylvia Herbert

We propose machine learning methods for solving fully nonlinear partial differential equations (PDEs) with convex Hamiltonian. Our algorithms are conducted in two steps. First the PDE is rewritten in its dual stochastic control…

Computational Finance · Quantitative Finance 2022-05-23 William Lefebvre , Grégoire Loeper , Huyên Pham

This paper introduces Deep Policy Iteration (DPI), a novel approach that integrates the strengths of Neural Networks with the stability and convergence advantages of Policy Iteration (PI) to address high-dimensional stochastic Mean Field…

Optimization and Control · Mathematics 2024-07-15 Mouhcine Assouli , Badr Missaoui

Option contracts on two underlying assets within uncertain volatility models have their worst-case and best-case prices determined by a two-dimensional (2D) Hamilton-Jacobi-Bellman (HJB) partial differential equation (PDE) with…

Computational Finance · Quantitative Finance 2025-06-19 Duy-Minh Dang , Hao Zhou

One of the key issues for imitation learning lies in making policy learned from limited samples to generalize well in the whole state-action space. This problem is much more severe in high-dimensional state environments, such as game…

Machine Learning · Computer Science 2021-07-02 Xin-Qiang Cai , Yao-Xiang Ding , Yuan Jiang , Zhi-Hua Zhou

Physics-informed neural networks (PINNs) have attracted a lot of attention in scientific computing as their functional representation of partial differential equation (PDE) solutions offers flexibility and accuracy features. However, their…

Machine Learning · Computer Science 2024-01-17 Xinquan Huang , Tariq Alkhalifah

In a more connected world, modeling multi-agent systems with hyperbolic partial differential equations (PDEs) offers a compact, physics-consistent description of collective dynamics. However, classical control tools need adaptation for…

Systems and Control · Electrical Eng. & Systems 2025-09-09 Katayoun Eshkofti , Matthieu Barreau

Deep learning-based numerical schemes such as Physically Informed Neural Networks (PINNs) have recently emerged as an alternative to classical numerical schemes for solving Partial Differential Equations (PDEs). They are very appealing at…

Numerical Analysis · Mathematics 2022-05-11 A. Beguinet , V. Ehrlacher , R. Flenghi , M. Fuente , O. Mula , A. Somacal

The physics-informed neural network (PINN) is effective in solving the partial differential equation (PDE) by capturing the physics constraints as a part of the training loss function through the Automatic Differentiation (AD). This study…

Computational Physics · Physics 2022-02-17 Zixue Xiang , Wei Peng , Weien Zhou , Wen Yao

Physics-informed neural networks (PINNs) were recently proposed in [1] as an alternative way to solve partial differential equations (PDEs). A neural network (NN) represents the solution while a PDE-induced NN is coupled to the solution NN,…

Computational Physics · Physics 2019-10-22 Xiaoli Chen , Jinqiao Duan , George Em Karniadakis