首页|Findings from Northeastern University Broaden Understanding of Machine Learning (Reinforcement Learning-Based Multimodal Model for the Stock Investment Portfoli o Management Task)
Findings from Northeastern University Broaden Understanding of Machine Learning (Reinforcement Learning-Based Multimodal Model for the Stock Investment Portfoli o Management Task)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on artificial intelligenc e is the subject of a new report. According to news reporting from Shenyang, Peo ple’s Republic of China, by NewsRx journalists, research stated, “Machine learni ng has been applied by more and more scholars in the field of quantitative inves tment, but traditional machine learning methods cannot provide high returns and strong stability at the same time. In this paper, a multimodal model based on re inforcement learning (RL) is constructed for the stock investment portfolio mana gement task.” Our news reporters obtained a quote from the research from Northeastern Universi ty: “Most of the previous methods based on RL have chosen the value-based RL met hods. Policy gradient-based RL methods have been proven to be superior to value- based RL methods by a growing number of research. Commonly used policy gradient- based reinforcement learning methods are DDPG, TD3, SAC, and PPO. We conducted c omparative experiments to select the most suitable method for the dataset in thi s paper. The final choice was DDPG. Furthermore, there will rarely be a way to r efine the raw data before training the agent. The stock market has a large amoun t of data, and the data are complex. If the raw stock market data are fed direct ly to the agent, the agent cannot learn the information in the data efficiently and quickly. We use state representation learning (SRL) to process the raw stock data and then feed the processed data to the agent. It is not enough to train t he agent using only stock data; we also added comment text data and image data. The comment text data comes from investors’ comments on stock bars. Image data a re derived from pictures that can represent the overall direction of the market. ”
Northeastern UniversityShenyangPeopl e’s Republic of ChinaAsiaCyborgsEmerging TechnologiesFinance and Investm entInvestment and FinanceMachine LearningReinforcement Learning
NETL
NSTL
