Building an Ethereum trading RL platform using price charts

This recipe will teach you to implement an Ethereum cryptocurrency trading environment for RL Agents with visual observations. The Agent will observe a price chart with Open, High, Low, Close, and Volume information over a specified time period to take an action (Hold, Buy, or Sell). The objective of the Agent is to maximize its reward, which is the profit you would make if you deployed the Agent to trade in your account!

Getting ready

To complete this recipe, make sure you have the latest version. You will need to activate the tf2rl-cookbook Python/conda virtual environment. Make sure that will update the environment so that it matches the latest conda environment specification file (tfrl-cookbook.yml), which can be found in this cookbook's code repository. If the following import statements run without any issues, you are ready to get started:

import os
import random
from typing import Dict
import cv2
import...