Reinforcement Learning with Pytorch

Reinforcement Learning with Pytorch, available at $59.99, has an average rating of 3.7, with 69 lectures, based on 395 reviews, and has 2694 subscribers.

You will learn about Reinforcement Learning basics Tabular methods Bellman equation Q Learning Deep Reinforcement Learning Learning from video input This course is ideal for individuals who are Anyone interested in artificial intelligence, data science, machine learning, deep learning and reinforcement learning. It is particularly useful for Anyone interested in artificial intelligence, data science, machine learning, deep learning and reinforcement learning.

Enroll now: Reinforcement Learning with Pytorch

Summary

Title: Reinforcement Learning with Pytorch

Price: $59.99

Average Rating: 3.7

Number of Lectures: 69

Number of Published Lectures: 69

Number of Curriculum Items: 69

Number of Published Curriculum Objects: 69

Original Price: 139.99

Quality Status: approved

Status: Live

What You Will Learn

Reinforcement Learning basics

Tabular methods

Bellman equation

Q Learning

Deep Reinforcement Learning

Learning from video input

Who Should Attend

Anyone interested in artificial intelligence, data science, machine learning, deep learning and reinforcement learning.

Target Audiences

Anyone interested in artificial intelligence, data science, machine learning, deep learning and reinforcement learning.

UPDATE:

All the code and installation instructions have been updated and verified to work with Pytorch 1.6 !!

Artificial Intelligence is dynamically edging its way into our lives. It is already broadly available and we use it – sometimes even not knowing it  – on daily basis. Soon it will be our permanent, every day companion.

And where can we place Reinforcement Learning in AI world? Definitely this is one of the most promising and fastest growing technologies that can eventually lead us to General Artificial Intelligence! We can see multiple examples where AI can achieve amazing results – from reaching super human level while playing games to solving real life problems (robotics, healthcare, etc).

Without a doubt it’s worth to know and understand it!

And that’s why this course has been created.

We will go through multiple topics, focusing on most important and practical details. We will start from very basic information, gradually building our understanding, and finally reaching the point where we will make our agent learn in human-like way – only from video input!

What’s important – of course we need to cover some theory – but we will mainly focus on practical part. Goal is to understand WHY and HOW.

In order to evaluate our algorithms we will use environments from – very popular – OpenAI Gym. We will start from basic text games, through more complex ones, up to challenging Atari games

What will be covered during the course ? 

– Introduction to Reinforcement Learning

– Markov Decision Process

– Deterministic and stochastic environments

– Bellman Equation

– Q Learning

– Exploration vs Exploitation

– Scaling up

– Neural Networks as function approximators

– Deep Reinforcement Learning

– DQN

– Improvements to DQN

– Learning from video input

– Reproducing some of most popular RL solutions

– Tuning parameters and  general recommendations

See you in the class!

Course Curriculum

Chapter 1: Welcome to the course

Lecture 1: Welcome!

Lecture 2: Before you start – Videos quality!

Lecture 3: Resources

Chapter 2: Introduction

Lecture 1: Introduction #1

Lecture 2: Introduction #2

Lecture 3: Introduction #3

Lecture 4: Introduction #4

Lecture 5: Environment setup / Installation

Lecture 6: Lab. OpenAI Gym #1

Lecture 7: Lab. OpenAI Gym #2

Lecture 8: Lab. OpenAI Gym #3

Lecture 9: Lab. OpenAI Gym #4

Chapter 3: Tabular methods

Lecture 1: Deterministic & Stochastic environments

Lecture 2: Rewards

Lecture 3: Bellman equation #1

Lecture 4: Bellman equation #2

Lecture 5: Resource – code

Lecture 6: Lab. Algorithm for deterministic environments #1

Lecture 7: Lab. Algorithm for deterministic environments #2

Lecture 8: Lab. Algorithm for deterministic environments #3

Lecture 9: Lab. Algorithm for deterministic environments #4

Lecture 10: Lab. Test with stochastic environment

Lecture 11: Q-Learning

Lecture 12: Lab. Algorithm for stochastic environments

Lecture 13: Exploration vs Exploitation

Lecture 14: Lab. Egreedy

Lecture 15: Lab. Adaptive egreedy

Lecture 16: Bonus Lab. Value iteration

Lecture 17: Homework

Lecture 18: Homework. Solution

Lecture 19: Homework. Tuning

Chapter 4: Scaling up

Lecture 1: Scaling up

Lecture 2: Neural Networks review

Lecture 3: Lab. Neural Networks review #1

Lecture 4: Lab. Neural Networks review #2

Lecture 5: Lab. Random CartPole

Lecture 6: Lab. Epsilon egreedy revisited

Lecture 7: Lab. Pytorch updated ( version 0.4.0 )

Lecture 8: Article. Pytorch updated! (further versions)

Lecture 9: Lab. OpenAI Gym + Neural Network #1

Lecture 10: Lab. OpenAI Gym + Neural Network #2

Lecture 11: Lab. OpenAI Gym + Neural Network #3

Lecture 12: Lab. Extended logging

Chapter 5: DQN

Lecture 1: Deep Reinforcement Learning

Lecture 2: Lab. Deep Reinforcement Learning

Lecture 3: Lab. Tuning challenge

Lecture 4: Experience Replay

Lecture 5: Lab. Experience Replay #1

Lecture 6: Lab. Experience Replay #2

Lecture 7: Lab. Experience Replay #3

Lecture 8: DQN

Lecture 9: Lab. DQN

Chapter 6: DQN Improvements

Lecture 1: Double DQN

Lecture 2: Lab. Double DQN

Lecture 3: Dueling DQN

Lecture 4: Lab. Dueling DQN

Lecture 5: Lab. Dueling DQN Challenge

Chapter 7: DQN with video output

Lecture 1: CNN Review

Lecture 2: Lab. Random Pong

Lecture 3: Saving & Loading the Model

Lecture 4: Lab. Pong from video output #1

Lecture 5: Lab. Pong from video output #2

Lecture 6: Lab. Pong from video output #3

Lecture 7: Lab. Pong from video output #4

Lecture 8: Lab. Pong from video output #5

Lecture 9: Lab. Pong from video output #6

Lecture 10: Potential improvements

Lecture 11: Article. Stacking 4 images together

Chapter 8: Final notes

Lecture 1: Whats next?

Instructors

Atamai AI Team
Data Science & AI Passion

Rating Distribution

1 stars: 20 votes

2 stars: 18 votes

3 stars: 50 votes

4 stars: 139 votes

5 stars: 168 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!