Cutting-Edge AI: Deep Reinforcement Learning in Python

Cutting-Edge AI: Deep Reinforcement Learning in Python

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 8.5 Hours | 3.28 GB

Apply deep learning to artificial intelligence and reinforcement learning using evolution strategies, A2C, and DDPG

Deep Reinforcement Learning is actually the combination of 2 topics: Reinforcement Learning and Deep Learning (Neural Networks).

While 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 Learning.

The 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.

Recently, these advances have allowed us to showcase just how powerful reinforcement learning can be.

We’ve seen how AlphaZero can master the game of Go using only self-play.

This is just a few years after the original AlphaGo already beat a world champion in Go.

We’ve seen real-world robots learn how to walk, and even recover after being kicked over, despite only being trained using simulation.

Simulation is nice because it doesn’t require actual hardware, which is expensive. If your agent falls down, no real damage is done.

We’ve seen real-world robots learn hand dexterity, which is no small feat.

Walking 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 subtle.

Imagine using your foot to do something you usually do with your hand, and you immediately understand why this would be difficult.

Last but not least – video games.

Even just considering the past few months, we’ve seen some amazing developments. AIs are now beating professional players in CS:GO and Dota 2.

Now that we know deep learning works with reinforcement learning, the question becomes: how do we improve these algorithms?

This 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.

Evolution 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.

What’s also great about this new course is the variety of environments we get to look at.

First, 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.

Second, 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.

Finally, we’re going to look at Flappy Bird, everyone’s favorite mobile game just a few years ago.

What you’ll learn

  • Understand a cutting-edge implementation of the A2C algorithm (OpenAI Baselines)
  • Understand and implement Evolution Strategies (ES) for AI
  • Understand and implement DDPG (Deep Deterministic Policy Gradient)
Table of Contents

Welcome
1 Introduction
2 Outline
3 Where to get the code

Review of Fundamental Reinforcement Learning Concepts
4 Review Section Introduction
5 The Explore-Exploit Dilemma
6 Markov Decision Processes (MDPs)
7 Monte Carlo Methods
8 Temporal Difference Learning (TD)
9 OpenAI Gym Warmup
10 Review Section Summary

A2C (Advantage Actor-Critic)
11 A2C Section Introduction
12 A2C
13 A2C Section Summary
14 A2C Theory (part 1)
15 A2C Theory (part 2)
16 A2C Theory (part 3)
17 A2C Demo
18 A2C Code – Rough Sketch
19 Multiple Processes
20 Environment Wrappers
21 Convolutional Neural Network

DDPG (Deep Deterministic Policy Gradient)
22 DDPG Section Introduction
23 Deep Q-Learning (DQN) Review
24 DDPG Theory
25 MuJoCo
26 DDPG Code (part 1)
27 DDPG Code (part 2)
28 DDPG Section Summary

ES (Evolution Strategies)
29 ES Section Introduction
30 ES Theory
31 Notes on Evolution Strategies
32 ES for Optimizing a Function
33 ES for Supervised Learning
34 Flappy Bird
35 ES for Flappy Bird in Code
36 ES for MuJoCo in Code
37 ES Section Summary

Appendix FAQ
38 What is the Appendix
39 What order should I take your courses in (part 1)
40 What order should I take your courses in (part 2)
41 Windows-Focused Environment Setup 2018
42 How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
43 Is this for Beginners or Experts Academic or Practical Fast or slow-paced
44 How to Succeed in this Course (Long Version)
45 How to Code by Yourself (part 1)
46 How to Code by Yourself (part 2)
47 Proof that using Jupyter Notebook is the same as not using it
48 Python 2 vs Python 3