Papers
Topics
Authors
Recent
Search
2000 character limit reached

Convergence Guarantees for Neural Network-Based Hamilton-Jacobi Reachability

Published 3 Oct 2024 in math.OC, cs.NA, math.NA, and stat.ML | (2410.02904v1)

Abstract: We provide a novel uniform convergence guarantee for DeepReach, a deep learning-based method for solving Hamilton-Jacobi-Isaacs (HJI) equations associated with reachability analysis. Specifically, we show that the DeepReach algorithm, as introduced by Bansal et al. in their eponymous paper from 2020, is stable in the sense that if the loss functional for the algorithm converges to zero, then the resulting neural network approximation converges uniformly to the classical solution of the HJI equation, assuming that a classical solution exists. We also provide numerical tests of the algorithm, replicating the experiments provided in the original DeepReach paper and empirically examining the impact that training with a supremum norm loss metric has on approximation error.

Authors (1)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. Hamilton–Jacobi Reachability: A Brief Overview and Recent Advances. In 2017 IEEE 56th Annual Conference on Decision and Control (CDC), pages 2242–2253. IEEE, 2017.
  2. DeepReach: A Deep Learning Approach to High-Dimensional Reachability. In IEEE International Conference on Robotics and Automation (ICRA), 2021.
  3. DGM: A deep learning algorithm for solving partial differential equations. Journal of Computational Physics, 375:1339–1364, 2018.
  4. Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. Commun. Math. Stat., 5(4):349–380, 2017.
  5. Generating Formal Safety Assurances for High-Dimensional Reachability, 2023.
  6. Convergence of the Deep Galerkin Method for Mean Field Control Problems, 2024.
  7. Deep Backward and Galerkin Methods for the Finite State Master Equation, 2024.
  8. Is L2superscript𝐿2L^{2}italic_L start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT Physics Informed Loss Always Suitable for Training Physics Informed Neural Network? In Advances in Neural Information Processing Systems, volume 35, pages 8278–8290. Curran Associates, Inc., 2022.
  9. Differential Games and Representation Formulas for Solutions of Hamilton-Jacobi-Isaacs Equations. Indiana University Mathematics Journal, 33(5):773–797, 1984.
  10. Verification of Neural Reachable Tubes via Scenario Optimization and Conformal Prediction, 2024.
  11. Imposing Exact Safety Specifications in Neural Reachable Tubes, 2024.
  12. Enhancing the Performance of DeepReach on High-Dimensional Systems through Optimizing Activation Functions, 2023.
  13. Ian Mitchell. A Robust Controlled Backward Reach Tube with (Almost) Analytic Solution for Two Dubins Cars. In Goran Frehse and Matthias Althoff, editors, ARCH20. 7th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH20), volume 74 of EPiC Series in Computing, pages 242–258. EasyChair, 2020.
  14. Kurt Hornik. Approximation capabilities of multilayer feedforward networks. Neural Networks, 4(2):251–257, 1991.
  15. User’s guide to viscosity solutions of second order partial differential equations. Bull. Amer. Math. Soc. (N.S.), 27(1):1–67, 1992.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.

Tweets

Sign up for free to view the 2 tweets with 2 likes about this paper.