The Red Queen's Trap: Limits of Deep Evolution in High-Frequency Trading

TL;DR

This paper critically examines the limitations of combining deep reinforcement learning and evolutionary algorithms in high-frequency trading, revealing systemic fragility and failure modes through empirical analysis of a hybrid trading system.

Contribution

It provides a detailed post-mortem analysis of a hybrid DRL-EC trading framework, identifying key failure modes and demonstrating the limits of model complexity without sufficient market information.

Findings

Training metrics showed high returns, but live performance decayed significantly.

Identified failure modes include overfitting to aleatoric uncertainty, survivor bias, and microstructure friction.

Increasing model complexity without information asymmetry worsens systemic fragility.

Abstract

The integration of Deep Reinforcement Learning (DRL) and Evolutionary Computation (EC) is frequently hypothesized to be the "Holy Grail" of algorithmic trading, promising systems that adapt autonomously to non-stationary market regimes. This paper presents a rigorous post-mortem analysis of "Galaxy Empire," a hybrid framework coupling LSTM/Transformer-based perception with a genetic "Time-is-Life" survival mechanism. Deploying a population of 500 autonomous agents in a high-frequency cryptocurrency environment, we observed a catastrophic divergence between training metrics (Validation APY $>300\%$) and live performance (Capital Decay $>70\%$). We deconstruct this failure through a multi-disciplinary lens, identifying three critical failure modes: the overfitting of \textit{Aleatoric Uncertainty} in low-entropy time-series, the \textit{Survivor Bias} inherent in evolutionary selection under high variance, and the mathematical impossibility of overcoming microstructure friction without order-flow data. Our findings provide empirical evidence that increasing model complexity in the absence of information asymmetry exacerbates systemic fragility.