Certifying Reward Alignment in Portfolio Reinforcement Learning
In briefChecking Whether Portfolio RL Agents Follow Their Intended Financial Goal
SummaryThis paper proposes a decision audit for portfolio reinforcement learning that separates reward misspecification from learning error, checking whether a learned policy implements its stated mean-variance objective. The method is tested in controlled markets and on historical US industry portfolios. The authors report that it quantifies whether a learned decision implements its financial objective, separately from backtest performance.