Self-Consistent Adjoint Policy Iteration for Constrained Dynamic Portfolio Choice
Abstract
We develop simulation-based policy iteration for continuous-time portfolio choice with predictable returns and convex constraints. Each outer step re-evaluates a fixed-latent open-loop backpropagation-through-time (OL-BPTT) adjoint after deployment and solves the constrained update. Shifted-adjoint cancellation controls the adjoint--HJB Hamiltonian-gradient discrepancy by the policy-improvement residual. For CRRA portfolios, exact HJB policy iteration identifies the optimal reduced value factor, while population OL-BPTT iteration converges globally when the adjoint update is directionally improving and approximate stationarity is asymptotically HJB-compatible. A theorem-matched occupation audit yields maximal 95% upper endpoints of $0.066$ for the primitive directional ratio and $0.074$ for a stronger norm-relative ratio, both against the half-step threshold $0.75$. In the high-precision $50−−50$ occupancy/broad-anchor design of a three-factor, fifty-asset benchmark, current-policy re-evaluation outperforms matched pooled refinement under the on-policy and broad evaluation laws.
Related
- Scalable Pontryagin-Guided Adjoint-to-Control Recovery for Constrained Dynamic Portfolio Choice
- Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design
- Multi-period Value-at-Risk Constrained Portfolio Optimization via DC Programming
- Constrained Mean Variance Portfolio Selection under Reflected Factor Dynamics: Stochastic Riccati Equations, Neumann Problems,and a Deep Solver
- Penalty-Uniform Localization for State-Constrained Policy Iteration
BibTeX
@misc{huh2026selfconsistent,
title = {{Self-Consistent Adjoint Policy Iteration for Constrained Dynamic Portfolio Choice}},
author = {Jeonggyu Huh and Yeoneung Kim and Seungwon Jeong},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.17808},
eprint = {2608.17808},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.17808},
}
RIS
TY - UNPB
TI - Self-Consistent Adjoint Policy Iteration for Constrained Dynamic Portfolio Choice
AU - Jeonggyu Huh
AU - Yeoneung Kim
AU - Seungwon Jeong
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2608.17808
UR - https://arxiv.org/abs/2608.17808
AB - We develop simulation-based policy iteration for continuous-time portfolio choice with predictable returns and convex constraints. Each outer step re-evaluates a fixed-latent open-loop backpropagation-through-time (OL-BPTT) adjoint after deployment and solves the constrained update. Shifted-adjoint cancellation controls the adjoint--HJB Hamiltonian-gradient discrepancy by the policy-improvement residual. For CRRA portfolios, exact HJB policy iteration identifies the optimal reduced value factor, while population OL-BPTT iteration converges globally when the adjoint update is directionally improving and approximate stationarity is asymptotically HJB-compatible. A theorem-matched occupation audit yields maximal 95% upper endpoints of $0.066$ for the primitive directional ratio and $0.074$ for a stronger norm-relative ratio, both against the half-step threshold $0.75$. In the high-precision $50−−50$ occupancy/broad-anchor design of a three-factor, fifty-asset benchmark, current-policy re-evaluation outperforms matched pooled refinement under the on-policy and broad evaluation laws.
ER -