06. Exercise 2: Solution

Objective: Your task is to identify the main reinforcement learning components for the scenario defined above.

Agent: Who is the agent in this scenario? The Trading Bot

State Representation: What information needs to be included in the state for the agent to make informed decisions? Describe the components of the state.

  1. Current Close Price
  2. 20-day Moving Average of Close Price
  3. Trade Volume

Action Space: List the possible actions the agent can take in the environment

  1. Buy Stock
  2. Hold Stock
  3. Sell Stock

Reward: Define the rewards that will guide the agent’s behavior. Specify the rewards for each action.

  1. Buy Stock - zero 
  2. Hold stock - zero
  3. Sell Stock - profit 

Next Concept