skip to Main Content
Sale

Advanced AI: Deep Reinforcement Learning with Python

$29.99 $12.00

4.88 (12 reviews)
Category:

Description

What you’ll learn

  • Build various deep learning agents (including DQN and A3C)
  • Apply a variety of advanced reinforcement learning algorithms to any problem
  • Q-Learning with Deep Neural Networks
  • Policy Gradient Methods with Neural Networks
  • Reinforcement Learning with RBF Networks
  • Use Convolutional Neural Networks with Deep Q-Learning

This course is all about the application of deep learning and neural networks to reinforcement learning.

If you’ve taken my first reinforcement learning class, then you know that reinforcement learning is on the bleeding edge of what we can do with AI.

Specifically, the combination of deep learning with reinforcement learning has led to AlphaGo beating a world champion in the strategy game Go, it has led to self-driving cars, and it has led to machines that can play video games at a superhuman level.

Reinforcement learning has been around since the 70s but none of this has been possible until now.

The world is changing at a very fast pace. The state of California is changing their regulations so that self-driving car companies can test their cars without a human in the car to supervise.

We’ve seen that reinforcement learning is an entirely different kind of machine learning than supervised and unsupervised learning.

Supervised and unsupervised machine learning algorithms are for analyzing and making predictions about data, whereas reinforcement learning is about training an agent to interact with an environment and maximize its reward.

Unlike supervised and unsupervised learning algorithms, reinforcement learning agents have an impetus – they want to reach a goal.

This is such a fascinating perspective, it can even make supervised / unsupervised machine learning and “data science” seem boring in hindsight. Why train a neural network to learn about the data in a database, when you can train a neural network to interact with the real-world?

While deep reinforcement learning and AI has a lot of potential, it also carries with it huge risk.

Bill Gates and Elon Musk have made public statements about some of the risks that AI poses to economic stability and even our existence.

As we learned in my first reinforcement learning course, one of the main principles of training reinforcement learning agents is that there are unintended consequences when training an AI.

AIs don’t think like humans, and so they come up with novel and non-intuitive solutions to reach their goals, often in ways that surprise domain experts – humans who are the best at what they do.

OpenAI is a non-profit founded by Elon Musk, Sam Altman (Y Combinator), and others, in order to ensure that AI progresses in a way that is beneficial, rather than harmful.

Part of the motivation behind OpenAI is the existential risk that AI poses to humans. They believe that open collaboration is one of the keys to mitigating that risk.

One of the great things about OpenAI is that they have a platform called the OpenAI Gym, which we’ll be making heavy use of in this course.

It allows anyone, anywhere in the world, to train their reinforcement learning agents in standard environments.

In this course, we’ll build upon what we did in the last course by working with more complex environments, specifically, those provided by the OpenAI Gym:

  • CartPole

  • Mountain Car

  • Atari games

To train effective learning agents, we’ll need new techniques.

We’ll extend our knowledge of temporal difference learning by looking at the TD Lambda algorithm, we’ll look at a special type of neural network called the RBF network, we’ll look at the policy gradient method, and we’ll end the course by looking at Deep Q-Learning (DQN) and A3C (Asynchronous Advantage Actor-Critic).

Thanks for reading, and I’ll 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:

  • College-level math is helpful (calculus, probability)

  • Object-oriented programming

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

  • Numpy coding: matrix and vector operations

  • Linear regression

  • Gradient descent

  • Know how to build ANNs and CNNs in Theano or TensorFlow

  • Markov Decision Proccesses (MDPs)

  • Know how to implement Dynamic Programming, Monte Carlo, and Temporal Difference Learning to solve MDPs

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)

Who this course is for:

  • Professionals and students with strong technical backgrounds who wish to learn state-of-the-art AI techniques

Course content

  • Introduction and Logistics
  • The Basics of Reinforcement Learning
  • OpenAI Gym and Basic Reinforcement Learning Techniques
  • TD Lambda
  • Policy Gradients
  • Deep Q-Learning
  • A3C
  • Theano and Tensorflow Basics Review
  • Setting Up Your Environment (FAQ by Student Request)
  • Extra Help With Python Coding for Beginners (FAQ by Student Request)

12 reviews for Advanced AI: Deep Reinforcement Learning with Python

  1. Luis Brito

    I can definitely see this course helping breaking through that initial barrier when it comes to learning a programming language. I’m positive I’ll finish it and hopefully master python by then.

  2. Abdallah Galal Abouhussein

    I would like to share my personnel experience, i`m very pleased and happy for taking this impressive course because Dr. Angela always makes it simple and easy to understand and always makes a precaution section before or after any bug that may appear to some students and also write or record the solution for us, and each word she said is very real and easy to understand.
    Thanks Dr. Angela
    Abdallah Galal

  3. Jiaqing Fan

    Very good course. Dr Angela explains things very clearly. The exercises are interactive and helpful.

    Angela’s voice is like ASMR in most lessons. So you won’t lose focus?

  4. Jaime Sánchez Blanco

    Every concept is very well explained so you can assimilate it, and the teacher insists in practicing daily to get the habit of programming. It really motivates to keep studying and practicing every day.

  5. Bradley Carouthers

    3 days in and I’ve already learned more than other training programs where I’ve put months in. Her teaching style is both efficient and effective.

    Edit: Now on day 29 and the course has held up my expectations and hopes. The rise in complexity is not too sharp, and every day feels like an accomplishment. Angela takes her time to explain things without rushing, yet is able to pack tons of information in nuggets of time.

    Still recommend supplemental exposure for a more wholesome grasp. Though, this should be quite enough

  6. Tommy Prévost

    Very good course.

    PROs: lots of coding exercises, clear explanations, great examples, adapted to 2021’s reality.

    CONs: past the first 30 lessons, many similar coding hands-on.

  7. Quang Tu

    I love all the lectures and challenges of this course. I finally find myself in love with coding. This is definitely a fun course. Thank you Angela for this great course.

  8. Fortunate Eze

    This course is nothing short of AMAZING. The level of love and sincere desire to see students succeed present in this course is a rare sight. This course is fun, it’s challenging, it’s suspense-filled, it makes you feel good about yourself solving those challenges. You don’t take this course and memorise codes, you take it and you know what you’re doing because you literally do it yourself.

    It couldn’t possibly be any more obvious that Angela brought out her whole heart, time, energy and resources to give us a course that if priced based on it’s value, many of us certainly can’t afford. I mean, she kept advising and encouraging us to keep going, because she knows the road could get bumpy, she made a few jokes and used funny animations so we smile along the way keeping it fun. Why some people can’t see this and would rather subscribe to trying to bend courses to fit their own personal preferences is beyond me, but I guess people will always be people.

    Dear Angela, I cannot speak for everyone but I certainly can speak for myself and I’m saying thank you. The efforts you put into making this course outstanding didn’t go unnoticed.

    Let as many of us as appreciate your efforts make you happy and energize you to create more life changing courses for us.

    Cheers.

  9. Chendaniel

    Just the course fits me. Learn by doing, it is easy to start and just follow the flow and at day 15 you realized how to program in Python. Then the magic happen. I am on day 27 and I am looking forward to start a new section everyday.

  10. Caspar Cheng

    Angela is my favourite teacher on Udemy, her courses always come with clear and concise demonstration, make it really easy to understand the content. Meanwhile, she also provide a lot of tips to encourage us moving further on the way of coding. I’m definitely a super fan of her. I had finished her web development boot camp and now I’m learning Python 100 days of code. This course is amazing as she provided one particular project for each day’s learning, which is, really useful and handy. Also, those projects are really interesting and won’t let me feel disappointed about myself. Although some of them are a little bit difficult, they’re still resolvable after some struggling and searching online. I’ll recommend this course for those who really want to learn Python well and write real python projects from scratch!

  11. Jonas Weber

    The course was awesome in the first half! Really helped me to get back to programming and learning new techniques. Also the course got way to much focused on web development in the second half, which I’m not really interested in and is redundand to your dedicated web development course. The lack of videos in the last quarter was rather sad. I really would’ve liked some video explanations for pandas and matplotlib. The challenges and capstone projects were great and challenging!
    All in all I can really recommend this course for beginners and those who want to learn python and/or get back to programming!

  12. Rohit Prasad

    Angela is the best teacher I have ever experienced. The way she explains all the topics and makes use of it in the projects is commendable. Thank you so much Angela for this course.

Leave a customer review

Your email address will not be published. Required fields are marked *

Back To Top