Artificial Intelligence: Reinforcement Learning in Python

Complete guide to Reinforcement Learning, with Stock Trading and Online Advertising Applications

4.78 (9982 reviews)
Udemy
platform
English
language
Data Science
category
45,727
students
14.5 hours
content
Feb 2024
last update
$74.99
regular price

What you will learn

Apply gradient-based supervised machine learning methods to reinforcement learning

Understand reinforcement learning on a technical level

Understand the relationship between reinforcement learning and psychology

Implement 17 different reinforcement learning algorithms

Understand important foundations for OpenAI ChatGPT, GPT-4

Description

Ever wondered how AI technologies like OpenAI ChatGPT and GPT-4 really work? In this course, you will learn the foundations of these groundbreaking applications.

When people talk about artificial intelligence, they usually don’t mean supervised and unsupervised machine learning.

These tasks are pretty trivial compared to what we think of AIs doing - playing chess and Go, driving cars, and beating video games at a superhuman level.

Reinforcement learning has recently become popular for doing all of that and more.

Much like deep learning, a lot of the theory was discovered in the 70s and 80s but it hasn’t been until recently that we’ve been able to observe first hand the amazing results that are possible.

In 2016 we saw Google’s AlphaGo beat the world Champion in Go.

We saw AIs playing video games like Doom and Super Mario.

Self-driving cars have started driving on real roads with other drivers and even carrying passengers (Uber), all without human assistance.

If that sounds amazing, brace yourself for the future because the law of accelerating returns dictates that this progress is only going to continue to increase exponentially.

Learning about supervised and unsupervised machine learning is no small feat. To date I have over TWENTY FIVE (25!) courses just on those topics alone.

And yet reinforcement learning opens up a whole new world. As you’ll learn in this course, the reinforcement learning paradigm is very from both supervised and unsupervised learning.

It’s led to new and amazing insights both in behavioral psychology and neuroscience. As you’ll learn in this course, there are many analogous processes when it comes to teaching an agent and teaching an animal or even a human. It’s the closest thing we have so far to a true artificial general intelligence.  What’s covered in this course?

  • The multi-armed bandit problem and the explore-exploit dilemma

  • Ways to calculate means and moving averages and their relationship to stochastic gradient descent

  • Markov Decision Processes (MDPs)

  • Dynamic Programming

  • Monte Carlo

  • Temporal Difference (TD) Learning (Q-Learning and SARSA)

  • Approximation Methods (i.e. how to plug in a deep neural network or other differentiable model into your RL algorithm)

  • How to use OpenAI Gym, with zero code changes

  • Project: Apply Q-Learning to build a stock trading bot

If you’re ready to take on a brand new challenge, and learn about AI techniques that you’ve never seen before in traditional supervised machine learning, unsupervised machine learning, or even deep learning, then this course is for you.

See you in class!


"If you can't implement it, you don't understand it"

  • Or as the great physicist Richard Feynman said: "What I cannot create, I do not understand".

  • My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch

  • Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?

  • After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times...


Suggested Prerequisites:

  • Calculus

  • Probability

  • Object-oriented programming

  • Python coding: if/else, loops, lists, dicts, sets

  • Numpy coding: matrix and vector operations

  • Linear regression

  • Gradient descent


WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • Check out the lecture "Machine Learning and AI Prerequisite Roadmap" (available in the FAQ of any of my courses, including the free Numpy course)


UNIQUE FEATURES

  • Every line of code explained in detail - email me any time if you disagree

  • No wasted time "typing" on the keyboard like other courses - let's be honest, nobody can really write code worth learning about in just 20 minutes from scratch

  • Not afraid of university-level math - get important details about algorithms that other courses leave out

Content

Welcome

Introduction
Where to get the Code
Strategy for Passing the Course
Course Outline

Return of the Multi-Armed Bandit

Problem Setup and The Explore-Exploit Dilemma
Applications of the Explore-Exploit Dilemma
Epsilon-Greedy
Updating a Sample Mean
Designing Your Bandit Program
Comparing Different Epsilons
Optimistic Initial Values
UCB1
Bayesian / Thompson Sampling
Thompson Sampling vs. Epsilon-Greedy vs. Optimistic Initial Values vs. UCB1
Nonstationary Bandits
Bandit Summary, Real Data, and Online Learning
(Optional) Alternative Bandit Designs

High Level Overview of Reinforcement Learning

What is Reinforcement Learning?
On Unusual or Unexpected Strategies of RL
Defining Some Terms

Build an Intelligent Tic-Tac-Toe Agent

Naive Solution to Tic-Tac-Toe
Components of a Reinforcement Learning System
Notes on Assigning Rewards
The Value Function and Your First Reinforcement Learning Algorithm
Tic Tac Toe Code: Outline
Tic Tac Toe Code: Representing States
Tic Tac Toe Code: Enumerating States Recursively
Tic Tac Toe Code: The Environment
Tic Tac Toe Code: The Agent
Tic Tac Toe Code: Main Loop and Demo
Tic Tac Toe Summary
Tic Tac Toe: Exercise

Markov Decision Proccesses

Gridworld
The Markov Property
Defining and Formalizing the MDP
Future Rewards
Value Function Introduction
Value Functions
Bellman Examples
Optimal Policy and Optimal Value Function
MDP Summary

Dynamic Programming

Intro to Dynamic Programming and Iterative Policy Evaluation
Gridworld in Code
Designing Your RL Program
Iterative Policy Evaluation in Code
Policy Improvement
Policy Iteration
Policy Iteration in Code
Policy Iteration in Windy Gridworld
Value Iteration
Value Iteration in Code
Dynamic Programming Summary

Monte Carlo

Monte Carlo Intro
Monte Carlo Policy Evaluation
Monte Carlo Policy Evaluation in Code
Policy Evaluation in Windy Gridworld
Monte Carlo Control
Monte Carlo Control in Code
Monte Carlo Control without Exploring Starts
Monte Carlo Control without Exploring Starts in Code
Monte Carlo Summary

Temporal Difference Learning

Temporal Difference Intro
TD(0) Prediction
TD(0) Prediction in Code
SARSA
SARSA in Code
Q Learning
Q Learning in Code
TD Summary

Approximation Methods

Approximation Intro
Linear Models for Reinforcement Learning
Features
Monte Carlo Prediction with Approximation
Monte Carlo Prediction with Approximation in Code
TD(0) Semi-Gradient Prediction
Semi-Gradient SARSA
Semi-Gradient SARSA in Code
Course Summary and Next Steps

Stock Trading Project with Reinforcement Learning

Stock Trading Project Section Introduction
Data and Environment
How to Model Q for Q-Learning
Design of the Program
Code pt 1
Code pt 2
Code pt 3
Code pt 4
Stock Trading Project Discussion

Appendix / FAQ

What is the Appendix?
Windows-Focused Environment Setup 2018
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
How to Code by Yourself (part 1)
How to Code by Yourself (part 2)
How to Succeed in this Course (Long Version)
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
Proof that using Jupyter Notebook is the same as not using it
Python 2 vs Python 3
What order should I take your courses in? (part 1)
What order should I take your courses in? (part 2)
BONUS: Where to get discount coupons and FREE deep learning material

Screenshots

Artificial Intelligence: Reinforcement Learning in Python - Screenshot_01Artificial Intelligence: Reinforcement Learning in Python - Screenshot_02Artificial Intelligence: Reinforcement Learning in Python - Screenshot_03Artificial Intelligence: Reinforcement Learning in Python - Screenshot_04

Reviews

Namratha
October 25, 2023
Great course, covers everything you need to know... listen to it 2x and you have a good chance of mastering the fundamentals of RL.
Jacob
July 2, 2023
This is a great course with a lot of information. I really like that the instructor reviews the code in each series, and he offers a lot of code to review. It also exposed me to a lot of the math behind RL, which I appreciated. Better yet, the instructor highlights those formulas in the code. Still, this was a tough course to complete. I spent a lot of time outside the course reviewing the material to help me understand a lot of the nuance that gets passed over in the material. It could also benefit from more repetition; there are a lot of statements like "I will skip this because we covered it earlier" (15 to 20 hours ago). I'm not blessed with an exceptional memory so that usually forced me to stop progressing and go look it up. That would not be terrible if the comment included a general marker for where to go look, like go look in lesson 15.
Geoff
June 29, 2023
Incredible amount of content. Well presented. Challenging but doable. Takes quite some time to absorb everything, but the feeling of accomplishment is great. Thanks Lazy Programmer!
Miles
June 22, 2023
This course was very well done. Some things toward the end got a bit hairy, but that's to be expected with a course so advanced. I would imagine it is very difficult to make it seem simple. I feel that figuring out how to make things work was kind of a learning experience in and of itself.
Kaivalya
June 16, 2023
Teaching is not upto the mark at beginner level. Why and how questions are not answered at all. Only high level of code reading has been done. Tutor must have to teach every algorithm by explaining theory behind it and then giving simple examples.
Andrew
March 7, 2023
I've never taken a course on Udemy that's given me so much value at this price. You can tell that Lazy Programmer is meticulous about making sure he covers every detail and making sure his students understand every step of the theory and code.
Aron
February 2, 2023
Course has lots of useful information. I got to learn lots of things I didn't know before, like dynamic programming and Monte Carlo, and how they're connected to Q-Learning. I always wanted to learn more about Reinforcement Learning and your course definitely is the best. Cheers!
Alexander
January 7, 2023
Very thorough and dense but very rewarding! I would recommend this to any aspiring data scientists and machine learners out there!
Alexander
December 15, 2022
This was an outstanding course, I've been in the AI space for a long time and was able to pick up a ton of great lessons here that apply to more than just reinforcement learning. Everything the instructor says is spot on, it's extremely thorough and organized well.
Keerthan
November 28, 2022
I had a great experience with this course and I feel that it was a good decision in choosing it. His teaching technique is praise worthy.
Chris-Jan
November 7, 2022
I have finished Computer Science at Vrije Universiteit in Amsterdam. The Computer Science masters there is rated fairly high. But it is not the same as as a masters in Statistics so I'm struggling with that part and the formulas do not help me in any way because I lack too much background knowledge. I did read some more on Bayesian statistics for the sole purpose of doing this course. But it is just too much. I'm glad I made it to the coding section because that allows me to get into Reinforcement Learning. I guess I just "speak another language".
Dhirendra
October 11, 2022
Thank you for your wonderful course. I am 45 years old with a totally different career and background. It was only 6 months ago that I began studying machine learning. I studied several hours everyday, practiced coding along in Python, and watched lectures on probability on YouTube. I was able to understand the course fully.
Biji
September 11, 2022
It was a great learning experience. Thank you. I'll keep coming back to the course to reference things for sure.
Hazem
August 30, 2022
Well, there are many problems with this course. Firstly, the materials for the course are not there. I contacted the instructor, but eventually, there was no response ( most of the students have the same issue since I read the many complaints in this regard). The other problematic issue is the way of describing, the instructor explains quickly, so it is hard to follow. This is not an easy course, so that the information can be grasped easily. I have the feeling that instructors speak quickly as he is reading an article to have short videos.
Vijay
July 13, 2022
It's awesome. I didn't know much about reinforcement learning earlier but now I can make a working agent to solve any task. Thank you very much.

Coupons

DateDiscountStatus
5/17/202179% OFF
expired
11/6/202170% OFF
expired

Charts

Price

Artificial Intelligence: Reinforcement Learning in Python - Price chart

Rating

Artificial Intelligence: Reinforcement Learning in Python - Ratings chart

Enrollment distribution

Artificial Intelligence: Reinforcement Learning in Python - Distribution chart
1080408
udemy ID
1/17/2017
course created date
8/27/2019
course indexed date
Bot
course submited by