Incorporating Cognitive Biases into Reinforcement Learning for Financial Decision-Making

TL;DR

This paper explores integrating cognitive biases like overconfidence and loss aversion into reinforcement learning models to better mimic human trading behavior and improve financial decision-making, though results are inconclusive.

Contribution

It introduces a novel approach to embed psychological biases into RL frameworks for finance, highlighting challenges and insights for future development.

Findings

Bias-augmented RL models show human-like trading patterns

Incorporating biases does not consistently improve risk-adjusted returns

The study offers lessons on the complexities of modeling human psychology in AI

Abstract

Financial markets are influenced by human behavior that deviates from rationality due to cognitive biases. Traditional reinforcement learning (RL) models for financial decision-making assume rational agents, potentially overlooking the impact of psychological factors. This study integrates cognitive biases into RL frameworks for financial trading, hypothesizing that such models can exhibit human-like trading behavior and achieve better risk-adjusted returns than standard RL agents. We introduce biases, such as overconfidence and loss aversion, into reward structures and decision-making processes and evaluate their performance in simulated and real-world trading environments. Despite its inconclusive or negative results, this study provides insights into the challenges of incorporating human-like biases into RL, offering valuable lessons for developing robust financial AI systems.