Multi-Trajectory Physics-Informed Neural Networks for HJB Equations with Hard-Zero Terminal Inventory: Optimal Execution on Synthetic & SPY Data
By: Anthime Valin
We study optimal trade execution with a hard-zero terminal inventory constraint, modeled via Hamilton-Jacobi-Bellman (HJB) equations. Vanilla PINNs often under-enforce this constraint and produce unstable controls. We propose a Multi-Trajectory PINN (MT-PINN) that adds a rollout-based trajectory loss and propagates a terminal penalty on terminal inventory via backpropagation-through-time, directly enforcing zero terminal inventory. A lightweight lambda-curriculum is adopted to stabilize training as the state expands from a risk-neutral reduced HJB to a risk-averse HJB. On the Gatheral-Schied single-asset model, MT-PINN aligns closely with their derived closed-form solutions and concentrates terminal inventory tightly around zero while reducing errors along optimal paths. We apply MT-PINNs on SPY intraday data, matching TWAP when risk-neutral, and achieving lower exposure and competitive costs, especially in falling windows, for higher risk-aversion.
Similar Papers
Ensemble based Closed-Loop Optimal Control using Physics-Informed Neural Networks
Machine Learning (CS)
Teaches computers to control machines perfectly.
Neural Policy Iteration for Stochastic Optimal Control: A Physics-Informed Approach
Machine Learning (CS)
Helps robots learn tasks faster and more reliably.
Trajectory Optimization for Minimum Threat Exposure using Physics-Informed Neural Networks
Systems and Control
Finds safest paths by avoiding danger.