Learning optimal portfolios with intrinsic rewards
A profitable stock trading strategy is crucial for financial institutions. However, it is difficult to find a successful trading strategy in the complex and dynamic financial market. A wise choice of an appropriate risk measure in trading problems is crucial to evaluate the investment performance as...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2022
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/156941 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | A profitable stock trading strategy is crucial for financial institutions. However, it is difficult to find a successful trading strategy in the complex and dynamic financial market. A wise choice of an appropriate risk measure in trading problems is crucial to evaluate the investment performance as well as to guide the RL trading agent to profit. In this dissertation, we are motivated to study the efficacy of learning optimal portfolios with intrinsic rewards. The main contributions of this dissertation include formally deriving the algorithm to incorporate the optimal intrinsic reward on Advantage Actor-Critic (A2C) RL algorithm and first applying the A2C algorithm with optimal intrinsic reward in finance environment. |
|---|