Neural Policy Iteration for Stochastic Optimal Control: A Physics-Informed Approach
By: Yeongjong Kim , Yeoneung Kim , Minseok Kim and more
Potential Business Impact:
Helps robots learn tasks faster and more reliably.
We propose a physics-informed neural network policy iteration (PINN-PI) framework for solving stochastic optimal control problems governed by second-order Hamilton--Jacobi--Bellman (HJB) equations. At each iteration, a neural network is trained to approximate the value function by minimizing the residual of a linear PDE induced by a fixed policy. This linear structure enables systematic $L^2$ error control at each policy evaluation step, and allows us to derive explicit Lipschitz-type bounds that quantify how value gradient errors propagate to the policy updates. This interpretability provides a theoretical basis for evaluating policy quality during training. Our method extends recent deterministic PINN-based approaches to stochastic settings, inheriting the global exponential convergence guarantees of classical policy iteration under mild conditions. We demonstrate the effectiveness of our method on several benchmark problems, including stochastic cartpole, pendulum problems and high-dimensional linear quadratic regulation (LQR) problems in up to 10D.
Similar Papers
Physics-informed approach for exploratory Hamilton--Jacobi--Bellman equations via policy iterations
Numerical Analysis
Teaches robots to learn tasks faster and smarter.
Ensemble based Closed-Loop Optimal Control using Physics-Informed Neural Networks
Machine Learning (CS)
Teaches computers to control machines perfectly.
Lyapunov-Based Physics-Informed Deep Neural Networks with Skew Symmetry Considerations
Systems and Control
Makes robots move more smoothly and accurately.