Tutorial 6: Portfolio Management with PPO

PPO

PPO strikes a balance between ease of implementation, sample complexity, and ease of tuning, trying to compute an update at each step that minimizes the cost function while ensuring the deviation from the previous policy is relativel small.

Notebook and Script

In this notebook, we implement the training and testing process of PPO based on the TradeMaster framework.

Tutorial6_PPO

And this is the script for training and testing.

train_ppo.py