Myopic Optimality: why reinforcement learning portfolio management strategies lose money
On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance
Abstract (arXiv)
Myopic optimization (MO) outperforms reinforcement learning (RL) in portfolio management: RL yields lower or negative returns, higher variance, larger costs, heavier CVaR, lower profitability, and greater model risk. We model execution/liquidation frictions with mark-to-market accounting. Using Malliavin calculus (Clark-Ocone/BEL), we derive policy gradients and risk shadow price, unifying HJB and KKT. This gives dual gap and convergence results: geometric MO vs. RL floors. We quantify phantom profit in RL via Malliavin policy-gradient contamination analysis and define a control-affects-dynamics (CAD) premium of RL indicating plausibly positive.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 16 Sep 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization
- 2025Accelerated Portfolio Optimization and Option Pricing with Reinforcement Learning
- 2026Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization
- 2026Concentrated Liquidity Provision: a Reinforcement Learning Perspective
- 2026Can Reinforcement Learning Efficiently Discover Price Manipulation?
- 2026Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approach
- 2026Realistic Market Impact Modeling for Reinforcement Learning Trading Environments
- 2025FR-LUX: Friction-Aware, Regime-Conditioned Policy Optimization for Implementable Portfolio Management