to Cutting-Edge AI!
is technically Deep Learning in
Python part 11 of my deep learning series, and my 3rd reinforcement
Reinforcement Learning is actually the combination of 2 topics: Reinforcement
Learning and Deep
Learning (Neural Networks).
both of these have been around for quite some time, it’s only been recently
that Deep Learning has really taken off, and along with it, Reinforcement
maturation of deep learning has propelled advances in reinforcement learning,
which has been around since the 1980s, although some aspects of it, such as the
Bellman equation, have been for much longer.
these advances have allowed us to showcase just how powerful reinforcement
learning can be.
seen how AlphaZero can master the
game of Go using only self-play.
is just a few years after the original AlphaGo already beat a world champion in
seen real-world robots learn how to walk, and even recover after being kicked
over, despite only being trained using simulation.
is nice because it doesn’t require actual hardware, which is expensive. If your
agent falls down, no real damage is done.
seen real-world robots learn hand dexterity, which is no small feat.
is one thing, but that involves coarse movements. Hand dexterity is complex –
you have many degrees of freedom and many of the forces involved are extremely
using your foot to do something you usually do with your hand, and you
immediately understand why this would be difficult.
but not least – video games.
just considering the past few months, we’ve seen some amazing developments. AIs
are now beating professional players in CS:GO and Dota
what makes this course different from the first two?
that we know deep learning works with reinforcement learning, the question
becomes: how do we improve these algorithms?
course is going to show you a few different ways: including the powerful A2C
(Advantage Actor-Critic) algorithm, the DDPG
(Deep Deterministic Policy Gradient) algorithm,
and evolution strategies.
strategies is a new and fresh take on reinforcement learning, that kind of
throws away all the old theory in favor of a more “black box”
approach, inspired by biological evolution.
also great about this new course is the variety of environments we get to look
we’re going to look at the classic Atari environments.
These are important because they show that reinforcement learning agents can
learn based on images alone.
we’re going to look at MuJoCo,
which is a physics simulator. This is the first step to building a robot that
can navigate the real-world and understand physics – we first have to show it
can work with simulated physics.
we’re going to look at Flappy Bird,
everyone’s favorite mobile game just a few years ago.
for reading, and I’ll see you in class!
you can’t implement it, you don’t understand it”
- Or as
the great physicist Richard Feynman said: “What I cannot create, I do
courses are the ONLY courses where you will learn how to implement machine
learning algorithms from scratch
courses will teach you how to plug in your data into a library, but do you
really need help with 3 lines of code?
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
- Object-oriented programming
coding: if/else, loops, lists, dicts, sets
coding: matrix and vector operations
- Linear regression
- Gradient descent
how to build a convolutional neural network (CNN) in TensorFlow
- Markov Decision Proccesses (MDPs)
WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:
out the lecture “Machine Learning and AI Prerequisite
Roadmap” (available in the FAQ of any of my courses, including the
free Numpy course)