Through this course, students will learn various reinforcement learning theories and implement them themselves, as well as create a reinforcement learning environment to test the reinforcement learning algorithm implemented using Unity Machine Learning Agents.
503 learners
Unity Development
Unity Machine Learning Agent
Creating a reinforcement learning environment
Reinforcement learning theory
Implementing reinforcement learning code
Implementation of reinforcement learning environment,
Easy and convenient with Unity!
Since AlphaGo's groundbreaking performance in 2016, interest in reinforcement learning , known to have been applied to AlphaGo, has grown significantly, and the enthusiasm remains strong. The key components of reinforcement learning are the reinforcement learning algorithm and the reinforcement learning environment, as shown below. These two components exchange information, including actions, states, and rewards, allowing the reinforcement learning algorithm to learn.
Since AlphaGo, reinforcement learning algorithms have made significant progress. In response, a variety of reinforcement learning environments have been released, including OpenAI GYM, Mujoco, Atari, GTA5, and Malmo. Most of these environments are game-based. While reinforcement learning is clearly an ideal algorithm for games, there has been a recent surge in attempts to apply it beyond games to diverse fields, including recommendation, robotics, drones, energy, and finance.
However, reinforcement learning environments for these diverse fields are still lacking. In particular, it's extremely difficult to expect an environment that precisely meets developers' specific requirements to be released. Even if you have a robot environment with a specific sensor configuration and joint structure that you want to apply reinforcement learning to, it may be impossible to even begin research without a publicly available reinforcement learning environment for that field.
About the environment
Sujeong
difficulty
For each environment
How to use this
difference
necessary
The environment
There may not be any
But in September 2017, Unity, one of the world's largest game engine companies, released a tool called Unity Machine-Learning Agent that could solve this problem.
In this lecture, you will learn how to implement various reinforcement learning environments using this Unity Machine Learning Agent, as well as the theory and code implementation of reinforcement learning algorithms applicable to those environments.
This course's content is identical to the book "Reinforcement Learning with PyTorch and Unity ML-Agents." Please be aware of this before attending.
The entire "Complete Mastery of Unity Machine Learning Agents" course will be divided into two sections: Basics and Applications. This lecture will cover the Basics section. The specific content covered in the Basics section is as follows:
The code for the environment we will create and the algorithms we will learn in this lecture is all included on GitHub .
The images below are the reinforcement learning environments you will implement in this lecture and the results of learning using the reinforcement learning algorithm you will implement.
Creating a Gridworld Environment
Creating a drone environment
Creating a kart racing environment
Q. I have never used Unity before. Can I still take the course?
Even beginners to Unity will find this course easy to follow, starting with installation and moving through the process of creating a simple environment. While it doesn't cover Unity in detail, after taking the course, you'll be able to create environments using assets from the Asset Store or by creating a simple environment yourself, creating a reinforcement learning environment.
Q. Do I need to be familiar with reinforcement learning to use machine learning agents?
Machine learning agents are tools that fundamentally support reinforcement learning, so a basic understanding of reinforcement learning concepts is essential for easier use. However, Unity Machine Learning Agents also provides a variety of reinforcement learning algorithms, allowing agents to learn within a reinforcement learning environment. This functionality allows you to easily use machine learning agents even without in-depth knowledge of reinforcement learning.
Q. Do I need a deep understanding of deep learning or extensive implementation experience to take this course?
If you've already implemented a model to classify MNIST data using PyTorch, you should be able to take this course without much difficulty. Even those with experience using TensorFlow 2.x should be able to take this course without difficulty if they just learn the basics of PyTorch.
Who is this course right for?
Developers interested in developing reinforcement learning environments
Students and researchers interested in the theory and implementation of reinforcement learning.
Need to know before starting?
Experience with Python and PyTorch
Basic Deep Learning Theory (ANN, CNN)
All
38 lectures ∙ (7hr 18min)
Course Materials:
All
24 reviews
4.2
24 reviews
Reviews 1
∙
Average Rating 5.0
5
A simple review by a non-major, liberal arts student "A lecture that provides a broad perspective and knowledge for beginners, and reinforcement learning and Unity tips for others" I bought the book before, but I came running when I heard that there was a video lecture...! This lecture is really full of information, such as creating a Unity environment, reinforcement learning theory, and practice. Even looking at it broadly, it is really rare to find a lecture that explains two fields in detail (actually, there aren't any...ㅠ). In addition, it is really diverse in detail, from simple reinforcement learning theory to practice and Unity environment building tips. In particular, it was really fun to do a simulation with Unity rather than just text, and I thought a lot about how I could create a machine learning agent....! If you are considering purchasing, I strongly recommend purchasing it!!
Reviews 1
∙
Average Rating 5.0
Reviews 10
∙
Average Rating 5.0
Reviews 1
∙
Average Rating 5.0
5
The lecture video is really good! Even if you don't have any specialized knowledge in reinforcement learning, you can understand it well. It's hard to find Korean explanation materials for Unity ML-Agent, but this one lecture is good because you can do all the basic design. I'm looking forward to not only the basics but also the intermediate and advanced levels. ㅎㅎ
Reviews 1
∙
Average Rating 5.0
5
I was able to gain a general understanding of how to implement reinforcement learning by configuring a learning environment in Unity. There are still errors in executing scripts in Unity, but I think it will get better in the future. It was very helpful, and I am looking forward to the application part.
Hello! Thank you so much for leaving a great review! What kind of errors are you getting in your Unity script? Please post them in the question box and I will answer as soon as possible! :)
Limited time deal ends in 00:58:02
$39.60
23%
$51.70
Check out other courses by the instructor!
Explore other courses in the same field!
![[Unity Level Up!] Modularly Developing Skill System강의 썸네일](https://cdn.inflearn.com/public/courses/333173/cover/1ebf894e-36b3-4254-b9f7-9c1e0f43e02b/333173.png?f=avif&w=420)
![[Tensorflow2] Complete conquest of Python machine learning - Marathon record prediction project강의 썸네일](https://cdn.inflearn.com/public/courses/324207/course_cover/1a79c7dc-1624-4d3a-95ff-79ba1e9c4025/python_machine_learning.png?f=avif&w=420)
![[ICT Archive] Big Data Core and Business Models강의 썸네일](https://cdn.inflearn.com/public/files/courses/338811/cover/01k44rs7zkwq0ehc8vqsy2mdtb?f=avif&w=420)
![[7-Day Complete] Pass MS AI-900 Certification in One Go강의 썸네일](https://cdn.inflearn.com/public/files/courses/338854/cover/01k4caartf5v7x2e574pq0wnp8?f=avif&w=420)
