Using Neural Networks to Compute Approximate and Guaranteed Feasible Hamilton-Jacobi-Bellman PDE Solutions
arXiv:1611.03158
Abstract
To sidestep the curse of dimensionality when computing solutions to Hamilton-Jacobi-Bellman partial differential equations (HJB PDE), we propose an algorithm that leverages a neural network to approximate the value function. We show that our final approximation of the value function generates near optimal controls which are guaranteed to successfully drive the system to a target state. Our framework is not dependent on state space discretization, leading to a significant reduction in computation time and space complexity in comparison with dynamic programming-based approaches. Using this grid-free approach also enables us to plan over longer time horizons with relatively little additional computation overhead. Unlike many previous neural network HJB PDE approximating formulations, our approximation is strictly conservative and hence any trajectories we generate will be strictly feasible. For demonstration, we specialize our new general framework to the Dubins car model and discuss how the framework can be applied to other models with higher-dimensional state spaces.
arXiv commentSubmitted to IEEE Conference on Decision and Control, 2017
References in corpus (1)
Cited by in corpus (7)
- On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton--Jacobi partial differential equations
- QRnet: optimal regulator design with LQR-augmented neural networks
- Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
- Lax-Oleinik-type formulas and efficient algorithms for certain high-dimensional optimal control problems
- Deep neural network approximation for high-dimensional parabolic Hamilton-Jacobi-Bellman equations
- Receding-Constraint Model Predictive Control using a Learned Approximate Control-Invariant Set
- Hopf-type representation formulas and efficient algorithms for certain high-dimensional optimal control problems