基于深度强化学习的 Actor-Critic 智能体股票交易策略：融入情感分析的方法研究
Financial Context-Rich Strategy for Actor-Critic based Agents: A Deep Reinforcement Learning Approach for Stock Trading
AI 导读
一篇 arXiv 论文提出面向股票交易的深度强化学习策略，在 Actor-Critic 智能体中部分及深度融入情感分析。研究涵盖仅策略优化的 A2C、PPO，以及结合 Q-learning 的 DDPG、TD3、SAC。结果显示，策略优化结合 Q-learning 的智能体在情感深度融入后，在利润最大化与风险规避交易中均显著且持续地表现更好。
正文 · 原文
Abstract:In modern financial markets, more than 3/4th of the large volume trade is executed by algorithmic trading based on advanced trading strategies to attain higher precision and speed than traditional human traders. The conventional strategies focused on price-based indicators are inadequate in capturing the market dynamism arising from real-world events such as social sentiments, political instability, or sudden economic shifts. With the rise of Deep Reinforcement Learning (DRL) and data availability, there is a requirement for more efficient algorithms that can incorporate these external factors in trading strategies. DRL has shown potential in simulating real-world scenarios and in simplifying complex decision-making since DRL agents can automate the trading process i.e. executing trades in a manner comparable to human traders. They have shown reliable performance since they can update their policies based on risk and quantitative factors. In this paper, we propose a DRL approach based on partial and deep-infusion of sentimental analysis. It features distinct policy designs of actor-critic-based agents: only policy optimization (A2C & PPO) and policy optimization along with Q-learning principles (DDPG, TD3 & SAC). Our findings reveal, that the agents based on policy optimization combined with Q-learning, significantly and consistently demonstrate improved performance upon sentiment deep-infusion in profit maximization as well as risk-averse trading.
| Subjects: | Artificial Intelligence (cs.AI); Computational Finance (q-fin.CP); Portfolio Management (q-fin.PM) |
| Cite as: | arXiv:2610.32237 [cs.AI] |
| (or arXiv:2610.32237v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32237 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hrishikesh Singh [view email]
[v1]
Fri, 23 Oct 2026 06:46:09 UTC (865 KB)
来源：arXiv cs.AI · arxiv.org