Develop Artificial Intelligence Applications using Reinforcement Learning in Python.
What you will learn
The concepts and fundamentals of reinforcement learning
The main algorithms including Q-Learning, SARSA as well as Deep Q-Learning.
How to formulate a problem in the context of reinforcement learning and MDP.
Apply the learned techniques to some hands-on experiments and real world projects.
Develop artificial intelligence applications using reinforcement learning.
Description
In this course we learn the concepts and fundamentals of reinforcement learning, it’s relation to artificial intelligence and machine learning, and how we can formulate a problem in the context of reinforcement learning and Markov Decision Process. We cover different fundamental algorithms including Q-Learning, SARSA as well as Deep Q-Learning. We present the whole implementation of two projects from scratch with Q-learning and Deep Q-Network.
English
language
Content
Introduction
Introduction
Course Structure
Environment Setup
Jump into Reinforcement Learning
Introduction
RL Applications
RL vs. Supervised and Unsupervised Learning
What is reinforcement learning?
RL Algorithms
Markov Decision Process
Optimal Policy
Bellman Equation
Q-Learning
Step-by-step Example
Sarsa
Deep Q-Network
Exploration vs. Exploitation
Define RL Problem – Examples
Reinforcement learning algorithms
SARSA algorithm
Hands-on Project 1 – Maze Problem
Overall Design
Create Project
Create files
Create Maze Environment class
Implement Building Maze Grid
Test build_maze method
Render and Reset methods
Implement getting next state and reward
Create Agent class
Implement adding states
Implement choosing action
Implement learn method
Create App
Implement main method
Implement plotting results
Run the App
Hands-on Project 2 – Stock Trading
Overall Design
Start project
Prepare dataset
Create Market Environment class
Implement getting data
Implement getting all states
Implement getting next state and reward
Create Agent class
Implement creating deep learning model and reset method
Implement getting action
Implement buy and sell
Implement experience replay
Create training app
Test training app
Create evaluation app
Implement plotting results
Run training and evaluation
Summary
Summary
