English

Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time

Optimization and Control 2020-05-05 v2 Machine Learning Systems and Control Systems and Control

Abstract

In this paper, we introduce Hamilton-Jacobi-Bellman (HJB) equations for Q-functions in continuous time optimal control problems with Lipschitz continuous controls. The standard Q-function used in reinforcement learning is shown to be the unique viscosity solution of the HJB equation. A necessary and sufficient condition for optimality is provided using the viscosity solution framework. By using the HJB equation, we develop a Q-learning method for continuous-time dynamical systems. A DQN-like algorithm is also proposed for high-dimensional state and control spaces. The performance of the proposed Q-learning algorithm is demonstrated using 1-, 10- and 20-dimensional dynamical systems.

Keywords

Cite

@article{arxiv.1912.10697,
  title  = {Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time},
  author = {Jeongho Kim and Insoon Yang},
  journal= {arXiv preprint arXiv:1912.10697},
  year   = {2020}
}

Comments

2nd Annual Conference on Learning for Dynamics and Control (L4DC)

R2 v1 2026-06-23T12:54:19.337Z