2026/03/30 by Lucas Riera Abbade, Lucas R. Abbade, Anna Helena Reali Costa · 1 voice
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Advanced Bandit Algorithms Research #Algorithmic trading #Baseline (sea) #Financial Markets and Investment Strategies #Margin (machine learning) #Portfolio #Reinforcement learning #Sharpe ratio #Stock Market Forecasting Methods #Trading strategy #Transaction cost #cs.CE #cs.LG
paper · pdf · doi:10.48550/arxiv.2603.29086
openalex publication_date 2026/03/30 · arxiv published 2026/03/30 · arxiv updated 2026/04/04 · openalex created_date 2026/04/08 · openalex updated_date 2026/07/28
Reinforcement learning (RL) has shown promise for trading, yet most open-source backtesting environments assume negligible or fixed transaction costs, causing agents to learn trading behaviors that fail under realistic execution. We introduce three Gymnasium-compatible trading environments -- MACE (Market-Adjusted Cost Execution) stock trading, margin trading, and portfolio optimization -- that integrate nonlinear market impact models grounded in the Almgren-Chriss framework and the empirically validated square-root impact law. Each environment provides pluggable cost models, permanent impact tracking with exponential decay, and comprehensive trade-level logging. We evaluate five DRL algorithms (A2C, PPO, DDPG, SAC, TD3) on the NASDAQ-100, comparing a fixed 10 bps baseline against the AC model with Optuna-tuned hyperparameters. Our results show that (i) the cost model materially changes both absolute performance and the relative ranking of algorithms across all three environments; (ii) the AC model produces dramatically different trading behavior, e.g., daily costs dropping from 200k to 8k with turnover falling from 19% to 1%; (iii) hyperparameter optimization is essential for constraining pathological trading, with costs dropping up to 82%; and (iv) algorithm-cost model interactions are strongly environment-specific, e.g., DDPG's OOS Sharpe jumps from -2.1 to 0.3 under AC in margin trading while SAC's drops from -0.5 to -1.2. We release the full suite as an open-source extension to FinRL-Meta.