This repository contains two jupyter notebooks. One contains five new features with appropriate visualization and another notebook attempts to provide code for a practical implementation of a PPO (Proximal Policy Optimization) agent for optimizing trading strategies. The latter is based on the paper 'An Adaptive Dual-level Reinforcement Learning Approach for Optimal Trade Execution (by Soohan Kim, Jimyeong Kim, Hong Kee Sul, Youngjoon Hong).'