Modern Reinforcement Learning: Actor-Critic Algorithms

Course Feature

Cost

Paid
Provider

Udemy
Certificate

Paid Certification
Language

English
Start Date

2020-10-04
Learners

No Information
Duration

No Information
Instructor

Phil Tabor

Add to Favorites

4.5

2,791 Ratings

This advanced course on deep reinforcement learning will teach you how to implement policy gradient, actor critic, deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and soft actor critic (SAC) algorithms in a variety of challenging environments. With a strong focus on dealing with environments with continuous action spaces, this course is perfect for those looking to do research into robotic control with deep reinforcement learning. You will learn a repeatable framework for quickly implementing the algorithms in advanced research papers, and master the answers to the fundamental questions in Actor-Critic methods. If you are a highly motivated and advanced student with prior course work in calculus, reinforcement learning, and deep learning, this course is for you.

Show All

Modern Reinforcement Learning: Actor-Critic Algorithms

Go to class

Course Overview

❗The content presented here is sourced directly from Udemy platform. For comprehensive course details, including enrollment information, simply click on the 'Go to class' link on our website.

Updated in [August 18th, 2023]

Skills and Knowledge:
By taking this course, students will acquire the skills and knowledge to implement policy gradient, actor critic, deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and soft actor critic (SAC) algorithms in a variety of challenging environments from the Open AIgym. Additionally, students will gain a repeatable framework for quickly implementing the algorithms in advanced research papers. Furthermore, students will gain an understanding of the fundamentals of reinforcement learning, including topics such as the Bellman Equation, Markov Decision Processes, Monte Carlo Prediction, Monte Carlo Control, Temporal Difference Prediction TD(0), and Temporal Difference Control with QLearning. Finally, students will gain an understanding of how to read deep reinforcement learning research papers and how to address the explore-exploit dilemma with a deterministic policy, as well as how to deal with overestimation bias and approximation errors in deep neural networks.
Professional Growth:
This course contributes to professional growth by providing students with the knowledge and skills to read and implement deep reinforcement learning research papers. By mastering the content in this course, students will be able to quickly implement advanced algorithms such as policy gradient, actor critic, deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and soft actor critic (SAC) in a variety of challenging environments. This will give them a quantum leap in their capabilities as an artificial intelligence engineer, and will put them in a league of their own among students who are reliant on others to break down complex ideas for them.
Further Education:
This course is suitable for preparing further education, as it covers advanced topics in deep reinforcement learning and provides a repeatable framework for quickly implementing algorithms in research papers. It also reviews core topics such as the Bellman Equation, Markov Decision Processes, Monte Carlo Prediction, Monte Carlo Control, Temporal Difference Prediction TD(0), and Temporal Difference Control with QLearning. Furthermore, it covers topics such as the REINFORCE algorithm, Deep Deterministic Policy Gradients (DDPG), Twin Delayed Deep Deterministic Policy Gradients (TD3), and Soft Actor Critic (SAC). This course is designed for highly motivated and advanced students who have prior course work in college level calculus, reinforcement learning, and deep learning.

Course Syllabus

Introduction

Fundamentals of Reinforcement Learning

Landing on the Moon with Policy Gradients & Actor Critic Methods

Deep Deterministic Policy Gradients (DDPG): Actor Critic with Continuous Actions

Twin Delayed Deep Deterministic Policy Gradients (TD3)

Soft Actor Critic

Show All

Recommended Courses

Artificial Intelligence IV - Reinforcement Learning in Java

4.7

Udemy 1,842 learners

Learn More

This course is perfect for those interested in Artificial Intelligence and Reinforcement Learning. It covers the mathematical background of Reinforcement Learning, such as Markov Decision Processes, value-iteration, policy-iteration and Q-learning. It also covers pathfinding algorithms with Q-learning and Q-learning with neural networks. This course is a great way to learn the state-of-the-art approach to Reinforcement Learning and gain a better understanding of Artificial Intelligence.

Machine Learning: Beginner Reinforcement Learning in Python

4.6

Udemy 497 learners

Learn More

This course is perfect for beginners to machine learning. In this course, you will learn to code a neural network in Python capable of delayed gratification. You will be introduced to the concept of reinforcement learning, and use the NChain game provided by the Open AI institute to understand how the computer can get a small reward if it goes backwards, but a much larger reward if it learns to make short term sacrifices by persistently pressing forwards. You will also learn Deep Q Learning - a revolutionary technique invented by Google DeepMind to teach neural networks to play chess, Go and Atari. Join this course to explore the exciting advances in artificial intelligence and learn to code a neural network in Python.

Advanced Reinforcement Learning in Python: from DQN to SAC

4.2

Udemy 1,234 learners

Learn More

This Advanced Reinforcement Learning course on Udemy is the most comprehensive of its kind. It will teach you to implement powerful Deep Reinforcement Learning algorithms in Python using PyTorch and PyTorch lightning. You will learn to create adaptive Artificial Intelligence agents that can solve decision-making tasks, combining Reinforcement Learning techniques with Neural Networks and Deep Learning methods. This course will also prepare you for the next courses in the series, where you will explore other advanced methods. With practical modules and jupyter notebooks, you will be able to develop your skills from scratch. Don't miss this opportunity to become an expert in Reinforcement Learning!

Advanced Reinforcement Learning in Python: cutting-edge DQNs

4.8

Udemy 891 learners

Learn More

This Advanced Reinforcement Learning course on Udemy is the most comprehensive of its kind. It will teach you to implement powerful Deep Reinforcement Learning algorithms in Python using PyTorch and PyTorch lightning. You will learn to create adaptive Artificial Intelligence agents that can solve decision-making tasks, combining Reinforcement Learning techniques with Neural Networks and Deep Learning methods. This course will also prepare you for the next courses in the series, where you will explore other advanced methods. With practical skills in mind, you will implement algorithms from scratch in jupyter notebooks. Don't miss out on this opportunity to learn the state of the art in Reinforcement Learning!