Multi-Agent Learning of Numerical Methods for Hyperbolic PDEs with Factored Dec-MDP
Factored decentralized Markov decision process (Dec-MDP) is a framework for modeling sequential decision making problems in multi-agent systems. In this paper, we formalize the learning of numerical methods for hyperbolic partial differential equations (PDEs), specifically the Weighted Essentially Non-Oscillatory (WENO) scheme, as a factored Dec-MDP problem. We show that different reward formulations lead to either reinforcement learning (RL) or behavior cloning, and a homogeneous policy could be learned for all agents under the RL formulation with a policy gradient algorithm. Because the trained agents only act on their local observations, the multi-agent system can be used as a general numerical method for hyperbolic PDEs and generalize to different spatial discretizations, episode lengths, dimensions, and even equation types.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision Makingreinforcement-learningReinforcement Learning (RL)Sequential Decision MakingSimilar Papers 제목 키워드 기반
Gamblets for opening the complexity-bottleneck of implicit schemes for hyperbolic and parabolic ODEs/PDEs with rough coefficients
Implicit schemes are popular methods for the integration of time dependent PDEs such as hyperbolic and parabolic PDEs. However the necessity to solve corresponding linear systems at each time step constitutes a complexit…
Backstepping Control of Coupled General Hyperbolic-Parabolic PDE-PDE Systems
This paper considers the backstepping state feedback and observer design for hyperbolic and parabolic PDEs, which are bidirectionally interconnected in a general coupling structure. Both PDE subsystems consist of coupled…
Backpropagation through Time and Space: Learning Numerical Methods with Multi-Agent Reinforcement Learning
We introduce Backpropagation Through Time and Space (BPTTS), a method for training a recurrent spatio-temporal neural network, that is used in a homogeneous multi-agent reinforcement learning (MARL) setting to learn nume…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)GoRINNs: Godunov-Riemann Informed Neural Networks for Learning Hyperbolic Conservation Laws
We present GoRINNs: numerical analysis-informed (shallow) neural networks for the solution of inverse problems of non-linear systems of conservation laws. GoRINNs is a hybrid/blended machine learning scheme based on high…
Vanishing Stacked-Residual PINN for State Reconstruction of Hyperbolic Systems
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…