Udemy - Advanced AI: Deep Reinforcement Learning in Python

  • CategoryOther
  • TypeTutorials
  • LanguageEnglish
  • Total size2.9 GB
  • Uploaded Bytutsnode
  • Downloads152
  • Last checkedMar. 09th '21
  • Date uploadedMar. 08th '21
  • Seeders 41
  • Leechers17
Your ISP and Government can track your torrent activity! Hide your IP with a VPN!

Infohash : 650162511775FAFF90D20973FE23B8FFF1B06390


Description

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

Requirements

Know reinforcement learning basics, MDPs, Dynamic Programming, Monte Carlo, TD Learning
College-level math is helpful
Experience building machine learning models in Python and Numpy
Know how to build ANNs and CNNs using Theano or Tensorflow

Last Updated 1/2021

Files:

Advanced AI Deep Reinforcement Learning in Python [TutsNode.com] - Advanced AI Deep Reinforcement Learning in Python 6. Deep Q-Learning
  • 7. Deep Q-Learning in Tensorflow for Breakout.mp4 (234.6 MB)
  • 7. Deep Q-Learning in Tensorflow for Breakout.srt (28.2 KB)
  • 8. Deep Q-Learning in Theano for Breakout.srt (28.1 KB)
  • 8. Deep Q-Learning in Theano for Breakout.mp4 (233.7 MB)
  • 2. Deep Q-Learning Techniques.srt (12.3 KB)
  • 6. Pseudocode and Replay Memory.srt (7.8 KB)
  • 5. Additional Implementation Details for Atari.srt (7.0 KB)
  • 10. Deep Q-Learning Section Summary.srt (6.0 KB)
  • 3. Deep Q-Learning in Tensorflow for CartPole.srt (5.8 KB)
  • 9. Partially Observable MDPs.srt (5.8 KB)
  • 4. Deep Q-Learning in Theano for CartPole.srt (5.4 KB)
  • 1. Deep Q-Learning Intro.srt (4.8 KB)
  • 6. Pseudocode and Replay Memory.mp4 (27.8 MB)
  • 3. Deep Q-Learning in Tensorflow for CartPole.mp4 (15.0 MB)
  • 2. Deep Q-Learning Techniques.mp4 (14.4 MB)
  • 4. Deep Q-Learning in Theano for CartPole.mp4 (13.8 MB)
  • 10. Deep Q-Learning Section Summary.mp4 (10.4 MB)
  • 5. Additional Implementation Details for Atari.mp4 (8.5 MB)
  • 9. Partially Observable MDPs.mp4 (7.6 MB)
  • 1. Deep Q-Learning Intro.mp4 (5.9 MB)
11. Effective Learning Strategies for Machine Learning (FAQ by Student Request)
  • 2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.srt (31.8 KB)
  • 4. Machine Learning and AI Prerequisite Roadmap (pt 2).srt (23.0 KB)
  • 3. Machine Learning and AI Prerequisite Roadmap (pt 1).srt (16.0 KB)
  • 1. How to Succeed in this Course (Long Version).srt (14.5 KB)
  • 2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.mp4 (39.0 MB)
  • 4. Machine Learning and AI Prerequisite Roadmap (pt 2).mp4 (37.6 MB)
  • 3. Machine Learning and AI Prerequisite Roadmap (pt 1).mp4 (29.3 MB)
  • 1. How to Succeed in this Course (Long Version).mp4 (18.3 MB)
2. The Basics of Reinforcement Learning
  • 2. Elements of a Reinforcement Learning Problem.srt (27.1 KB)
  • 11. Q-Learning.srt (19.0 KB)
  • 9. Solving the Bellman Equation with Reinforcement Learning (pt 2).srt (15.5 KB)
  • 4. Markov Decision Processes (MDPs).srt (13.3 KB)
  • 6. Value Functions and the Bellman Equation.srt (12.8 KB)
  • 8. Solving the Bellman Equation with Reinforcement Learning (pt 1).srt (12.4 KB)
  • 3. States, Actions, Rewards, Policies.srt (11.7 KB)
  • 7. What does it mean to “learn”.srt (9.3 KB)
  • 1. Reinforcement Learning Section Introduction.srt (8.8 KB)
  • 10. Epsilon-Greedy.srt (7.9 KB)
  • 12. How to Learn Reinforcement Learning.srt (7.8 KB)
  • 5. The Return.srt (6.7 KB)
  • 13. Suggestion Box.srt (4.7 KB)
  • 2. Elements of a Reinforcement Learning Problem.mp4 (105.2 MB)
  • 11. Q-Learning.mp4 (67.1 MB)
  • 9. Solving the Bellman Equation with Reinforcement Learning (pt 2).mp4 (57.3 MB)
  • 4. Markov Decision Processes (MDPs).mp4 (50.9 MB)
  • 6. Value Functions and the Bellman Equation.mp4 (48.1 MB)
  • 3. States, Actions, Rewards, Policies.mp4 (44.5 MB)
  • 8. Solving the Bellman Equation with Reinforcement Learning (pt 1).mp4 (42.9 MB)
  • 10. Epsilon-Greedy.mp4 (41.8 MB)
  • 1. Reinforcement Learning Section Introduction.mp4 (41.0 MB)
  • 12. How to Learn Reinforcement Learning.mp4 (40.6 MB)
  • 7. What does it mean to “learn”.mp4 (32.9 MB)
  • 5. The Return.mp4 (23.8 MB)
  • 13. Suggestion Box.mp4 (16.1 MB)
1. Introduction and Logistics
  • 2.1 Github Link.html (0.1 KB)
  • 3. Anyone Can Succeed in this Course.srt (18.0 KB)
  • 1. Introduction and Outline.srt (11.3 KB)
  • 2. Where to get the Code.srt (7.5 KB)
  • 4. Tensorflow or Theano - Your Choice!.srt (5.4 KB)
  • 3. Anyone Can Succeed in this Course.mp4 (83.9 MB)
  • 1. Introduction and Outline.mp4 (50.5 MB)
  • 2. Where to get the Code.mp4 (30.4 MB)
  • 4. Tensorflow or Theano - Your Choice!.mp4 (18.9 MB)
10. Extra Help With Python Coding for Beginners (FAQ by Student Request)
  • 1. How to Code by Yourself (part 1).srt (22.8 KB)
  • 3. Proof that using Jupyter Notebook is the same as not using it.srt (14.1 KB)
  • 2. How to Code by Yourself (part 2).srt (13.3 KB)
  • 5. Is Theano Dead.srt (12.9 KB)
  • 4. Python 2 vs Python 3.srt (6.1 KB)
  • 3. Proof that using Jupyter Notebook is the same as not using it.mp4 (78.2 MB)
  • 1. How to Code by Yourself (part 1).mp4 (24.5 MB)
  • 5. Is Theano Dead.mp4 (17.8 MB)
  • 2. How to Code by Yourself (part 2).mp4 (14.8 MB)
  • 4. Python 2 vs Python 3.mp4 (7.8 MB)
7. A3C
  • 5. A3C - Code pt 4.srt (21.2 KB)
  • 1. A3C - Theory and Outline.srt (20.3 KB)
  • 4. A3C - Code pt 3.srt (9.0 KB)
  • 3. A3C - Code pt 2.srt (8.3 KB)
  • 2. A3C - Code pt 1 (Warmup).srt (7.8 KB)
  • 7. Course Summary.srt (6.0 KB)
  • 6. A3C - Section Summary.srt (2.6 KB)
  • 5. A3C - Code pt 4.mp4 (184.3 MB)
  • 4. A3C - Code pt 3.mp4 (84.5 MB)
  • 1. A3C - Theory and Outline.mp4 (71.8 MB)
  • 3. A3C - Code pt 2.mp4 (57.6 MB)
  • 2. A3C - Code pt 1 (Warmup).mp4 (50.1 MB)
  • 7. Course Summary.mp4 (9.4 MB)
  • 6. A3C - Section Summary.mp4 (8.9 MB)
9. Setting Up Your Environment (FAQ by Student Request)
  • 1. Windows-Focused Environment Setup 2018.srt (20.1 KB)
  • 2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.srt (14.5 KB)
  • 1. Windows-Focused Environment Setup 2018.mp4 (186.2 MB)
  • 2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.mp4 (43.9 MB)
5. Policy Gradients
  • 1. Policy Gradient Methods.srt (14.8 KB)
  • 7. Mountain Car Continuous Tensorflow.srt (10.3 KB)
  • 6. Mountain Car Continuous Theano.srt (9.9 KB)
  • 2. Policy Gradient in TensorFlow for CartPole.srt (8.7 KB)
  • 9. Mountain Car Continuous Theano (v2).srt (8.3 KB)
  • 8. Mountain Car Continuous Tensorflow (v2).

Code:

  • udp://inferno.demonoid.pw:3391/announce
  • udp://tracker.openbittorrent.com:80/announce
  • udp://tracker.opentrackr.org:1337/announce
  • udp://torrent.gresille.org:80/announce
  • udp://glotorrents.pw:6969/announce
  • udp://tracker.leechers-paradise.org:6969/announce
  • udp://tracker.pirateparty.gr:6969/announce
  • udp://tracker.coppersurfer.tk:6969/announce
  • udp://ipv4.tracker.harry.lu:80/announce
  • udp://9.rarbg.to:2710/announce
  • udp://shadowshq.yi.org:6969/announce
  • udp://tracker.zer0day.to:1337/announce