HOT
blank

Advanced Reinforcement Learning: policy gradient methods

Development

Rating4.8
Enroll Now

Advanced Reinforcement Learning: policy gradient methods, available at $69.99, has an average rating of 4.8, with 96 lectures, based on 81 reviews, and has 1400 subscribers.

You will learn about Master some of the most advanced Reinforcement Learning algorithms. Learn how to create AIs that can act in a complex environment to achieve their goals. Create from scratch advanced Reinforcement Learning agents using Python's most popular tools (PyTorch Lightning, OpenAI gym, Optuna) Learn how to perform hyperparameter tuning (Choosing the best experimental conditions for our AI to learn) Fundamentally understand the learning process for each algorithm. Debug and extend the algorithms presented. Understand and implement new algorithms from research papers. This course is ideal for individuals who are Developers who want to get a job in Machine Learning. or Data scientists/analysts and ML practitioners seeking to expand their breadth of knowledge. or Robotics students and researchers. or Engineering students and researchers. It is particularly useful for Developers who want to get a job in Machine Learning. or Data scientists/analysts and ML practitioners seeking to expand their breadth of knowledge. or Robotics students and researchers. or Engineering students and researchers.

Enroll now: Advanced Reinforcement Learning: policy gradient methods

Summary

Title: Advanced Reinforcement Learning: policy gradient methods

Price: $69.99

Average Rating: 4.8

Number of Lectures: 96

Number of Published Lectures: 96

Number of Curriculum Items: 96

Number of Published Curriculum Objects: 96

Original Price: $199.99

Quality Status: approved

Status: Live

What You Will Learn

  • Master some of the most advanced Reinforcement Learning algorithms.
  • Learn how to create AIs that can act in a complex environment to achieve their goals.
  • Create from scratch advanced Reinforcement Learning agents using Python's most popular tools (PyTorch Lightning, OpenAI gym, Optuna)
  • Learn how to perform hyperparameter tuning (Choosing the best experimental conditions for our AI to learn)
  • Fundamentally understand the learning process for each algorithm.
  • Debug and extend the algorithms presented.
  • Understand and implement new algorithms from research papers.

Who Should Attend

  • Developers who want to get a job in Machine Learning.
  • Data scientists/analysts and ML practitioners seeking to expand their breadth of knowledge.
  • Robotics students and researchers.
  • Engineering students and researchers.

Target Audiences

  • Developers who want to get a job in Machine Learning.
  • Data scientists/analysts and ML practitioners seeking to expand their breadth of knowledge.
  • Robotics students and researchers.
  • Engineering students and researchers.

This is the most complete Reinforcement Learning course series on Udemy. In it, you will learn to implement some of the most powerful Deep Reinforcement Learning algorithms in Python using PyTorch and PyTorch lightning. You will implement from scratch adaptive algorithms that solve control tasks based on experience. You will learn to combine these techniques with Neural Networks and Deep Learning methods to create adaptive Artificial Intelligence agents capable of solving decision-making tasks.

This course will introduce you to the state of the art in Reinforcement Learning techniques. It will also prepare you for the next courses in this series, where we will explore other advanced methods that excel in other types of task.

The course is focused on developing practical skills. Therefore, after learning the most important concepts of each family of methods, we will implement one or more of their algorithms in jupyter notebooks, from scratch.

Leveling modules: 

– Refresher: The Markov decision process (MDP).

– Refresher: Monte Carlo methods.

– Refresher: Temporal difference methods.

– Refresher: N-step bootstrapping.

– Refresher: Brief introduction to Neural Networks.

– Refresher: Policy gradient methods.

Advanced Reinforcement Learning:

– REINFORCE

– REINFORCE for continuous action spaces

– Advantage actor-critic (A2C)

– Trust region methods

– Proximal policy optimization (PPO)

– Generalized advantage estimation (GAE)

– Trust region policy optimization (TRPO)

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Lecture 2: Reinforcement Learning series

Lecture 3: Google Colab

Lecture 4: Where to begin

Lecture 5: Complete code

Lecture 6: Connect with me on social media

Chapter 2: Refresher: The Markov Decision Process (MDP)

Lecture 1: Elements common to all control tasks

Lecture 2: The Markov decision process (MDP)

Lecture 3: Types of Markov decision process

Lecture 4: Trajectory vs episode

Lecture 5: Reward vs Return

Lecture 6: Discount factor

Lecture 7: Policy

Lecture 8: State values v(s) and action values q(s,a)

Lecture 9: Bellman equations

Lecture 10: Solving a Markov decision process

Chapter 3: Refresher: Monte Carlo methods

Lecture 1: Monte Carlo methods

Lecture 2: Solving control tasks with Monte Carlo methods

Lecture 3: On-policy Monte Carlo control

Chapter 4: Refresher: Temporal difference methods

Lecture 1: Temporal difference methods

Lecture 2: Solving control tasks with temporal difference methods

Lecture 3: Monte Carlo vs temporal difference methods

Lecture 4: SARSA

Lecture 5: Q-Learning

Lecture 6: Advantages of temporal difference methods

Chapter 5: Refresher: N-step bootstrapping

Lecture 1: N-step temporal difference methods

Lecture 2: Where do n-step methods fit?

Lecture 3: Effect of changing n

Chapter 6: Refresher: Brief introduction to Neural Networks

Lecture 1: Function approximators

Lecture 2: Artificial Neural Networks

Lecture 3: Artificial Neurons

Lecture 4: How to represent a Neural Network

Lecture 5: Stochastic Gradient Descent

Lecture 6: Neural Network optimization

Chapter 7: Refresher: REINFORCE

Lecture 1: Policy gradient methods

Lecture 2: Representing policies using neural networks

Lecture 3: Policy performance

Lecture 4: The policy gradient theorem

Lecture 5: REINFORCE

Lecture 6: Parallel learning

Lecture 7: Entropy regularization

Lecture 8: REINFORCE 2

Chapter 8: PyTorch Lightning

Lecture 1: PyTorch Lightning

Lecture 2: Link to the code notebook

Lecture 3: Create the policy

Lecture 4: Create the environment

Lecture 5: Create the dataset

Lecture 6: Create the REINFORCE algorithm – Part 1

Lecture 7: Create the REINFORCE algorithm – Part 2

Lecture 8: Check the resulting agent

Chapter 9: REINFORCE for continuous control tasks

Lecture 1: REINFORCE for continuous action spaces

Lecture 2: Link to the code notebook

Lecture 3: Create the policy

Lecture 4: Create the inverted pendulum environment

Lecture 5: Create the dataset

Lecture 6: Creating the algorithm – Part 1

Lecture 7: Creating the algorithm – Part 2

Lecture 8: Check the resulting agent

Chapter 10: Advantage Actor Critic (A2C)

Lecture 1: A2C

Lecture 2: Link to the code notebook

Lecture 3: Create the policy and value network

Lecture 4: Create the environment

Lecture 5: Create the dataset

Lecture 6: Implement A2C – Part 1

Lecture 7: Implement A2C – Part 2

Lecture 8: Check the resulting agent

Chapter 11: Trust region methods

Lecture 1: Line search vs trust region methods

Lecture 2: Line search methods

Lecture 3: Trust region methods 1

Lecture 4: Kullback-Leibler divergence

Lecture 5: Trust region methods 2

Lecture 6: Trust region methods 3

Chapter 12: Proximal Policy Optimization (PPO)

Lecture 1: Proximal Policy Optimization

Lecture 2: Link to the code notebook

Lecture 3: Create the environment

Lecture 4: Create the dataset

Lecture 5: Create the PPO algorithm – Part 1

Lecture 6: Create the PPO algorithm – Part 2

Lecture 7: Check the resulting agent

Chapter 13: Generalized Advantage Estimation (GAE)

Lecture 1: Generalized Advantage Estimation

Lecture 2: Link to the code notebook

Lecture 3: Create the Half Cheetah environment

Lecture 4: Create the dataset

Lecture 5: PPO with generalized advantage estimation – Part 1

Lecture 6: PPO with generalized advantage estimation – Part 2

Lecture 7: Checking the resulting agent

Chapter 14: Trust Region Policy Optimization (TRPO)

Instructors

Rating Distribution

  • 1 stars: 2 votes
  • 2 stars: 2 votes
  • 3 stars: 1 votes
  • 4 stars: 20 votes
  • 5 stars: 56 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!

You may also like

Top 10 Ethical AI Courses to Learn in November 2024

Top 10 Game Development Courses to Learn in November 2024

Top 10 Software Testing Courses to Learn in November 2024