Reinforcement learning
In this experiment of algorithmic portfolio management, the portfolio managing agent performs the trading actions in the financial market environment powered by reinforcement learning. The environment comprises all the available assets of the given market. Since the environment is large and complex, it's impossible for the agent to fully observe the state, that is, to get all the information of the state. Moreover, since the full order history of the market is too huge to process, sub-sampling from the order history data simplifies the processing of state representation of the environment. These sub-sampling methods include:
- Periodic feature extraction: Discretizes the time into many periods and then extracts the opening, highest, lowest, and closing prices for each of those periods
- Data slicing: Consider only the data from recent time periods and avoid the older historical data in order to do current state representation of the environment
The agent made some buying...
