inflearn logo

From Introduction to Reinforcement Learning to Deep Q-learning/Policy Gradient

Recently, all the remarkable achievements in the field of artificial intelligence are being announced in the area of reinforcement learning. This covers reinforcement learning technology—which is bringing about true innovation in AI such as robotics, autonomous driving, and humanoid machines—from basic to advanced levels in an easy-to-understand way for beginners.

(4.7) 38 reviews

415 learners

Level Intermediate

Course period Unlimited

Python
Python
Deep Learning(DL)
Deep Learning(DL)
Reinforcement Learning(RL)
Reinforcement Learning(RL)
PyTorch
PyTorch
Python
Python
Deep Learning(DL)
Deep Learning(DL)
Reinforcement Learning(RL)
Reinforcement Learning(RL)
PyTorch
PyTorch

Reviews from Early Learners

4.7

5.0

김두한

100% enrolled

The Only Korean-Language Course with “Just the Right Mix of Theory and Practice” Pros 1. It doesn’t get bogged down in deriving equations from the start. Instead, it explains concepts using a reasonable amount of math and then moves straight into implementation, which makes it easy to put what you’ve learned into practice. 2. It pairs extremely well with Hyukpenheim’s reinforcement learning theory lectures on YouTube, some of which are paid. 3. Courses that are suitable for beginners in reinforcement learning are very rare. They tend to offer either theory alone or code without much explanation. In that sense, this course—with its balanced mix of theory and implementation—was personally the most helpful. I took three courses: the KOCW open course, Hyukpenheim’s theory lectures, and this one, and this was the best. Cons The policy-based section only goes as far as REINFORCE. It would be perfect if it covered Actor-Critic, A2C, DDPG, and PPO as well. However, once you understand the general policy gradient formula and learn REINFORCE as an example, the other algorithms are only minor variations, so I think it should be entirely possible to find resources and implement them on your own using what you learned in the course. Thank you. I learned a lot. This was the only proper Korean-language reinforcement learning course that included both theory and practice. I felt lost after watching theory-only courses, but after taking this one, I think I’ll be able to study and implement individual algorithm papers on my own.

5.0

kti1452

100% enrolled

It’s great that I can neatly organize reinforcement learning theory and internalize it through hands-on practice implementing actual code!

5.0

tkpark

31% enrolled

Thank you for explaining information about a new field to me in an easy-to-understand way.

What you will gain after the course

  • The history of reinforcement learning and the process of major technological transitions

  • Traditional Reinforcement Learning Theory

  • Practical technical skills for implementing reinforcement learning models

  • Modern Reinforcement Learning Theory Applying Deep Learning

  • PyTorch Basics

Enter as a beginner, leave as a practitioner!
The A to Z of reinforcement learning in just one lecture 🤩

Reinforcement Learning,
learn at a beginner's level! 📖

Unlike the data-centric deep learning and machine learning we typically know, reinforcement learning is an artificial intelligence training method that has developed around trial and error. With the recent advancements in deep learning, the two fields have converged, leading to the application of various reinforcement learning techniques in solving real-world problems. Today, it has established itself as a crucial field of artificial intelligence and algorithms with many success stories.

This course covers reinforcement learning from basics to advanced knowledge using PyTorch as a deep learning tool. We have made an effort to explain concepts easily without using difficult mathematics, and the course is conducted with a focus on practice so that it can be applied to real-world tasks.

A proven curriculum currently being taught in actual offline classes

Lecture materials with improved quality based on feedback from on-site students

Practice-oriented practical lecture


Target Audience / Course Objectives 🙆‍♀️

 

Those interested in reinforcement learning

Developers looking to apply reinforcement learning to their work

Those who want to broaden their knowledge of artificial intelligence


What you will learn 📚

1. History of Reinforcement Learning

2. Dynamic Programming 

3. Monte Carlo Method

 

4. Temporal Difference Method

5. Deep Q-learning

The lecture comes with hands-on practice! 🔥


Notes before taking the course 📢

Practice Environment

  • Windows, Mac, and Linux are all acceptable.
  • Tools used: VSCODE, Jupyter Notebook, Colab
  • PC Specifications: General specifications

Learning Materials

  • Format of provided learning materials (PPT, cloud links, text, source code, assets, programs, example problems, etc.)
  • Quantity and capacity, and other characteristics of learning materials

Wait! ✋ Basic knowledge of Python is required to take this course.

I recommend courses that are good to take together by type.

Type 1 Those who lack basic Python skills but need an intensive crash course due to a lack of time


Type 2 Those who want to learn the prerequisite knowledge for machine learning/deep learning step-by-step


Type 3 Those who want to learn the Python language properly and thoroughly


Expected Q&A 💬

Q. Which programming language is used?

Algorithms are implemented using the Python language.

Q. Is prior knowledge of deep learning required?

Yes. Please refer to the prerequisite course guide.

Q. Which deep learning framework do you use?

We are implementing deep learning networks using PyTorch. Since a PyTorch crash course is included in the lecture, it is fine even if you do not know how to use PyTorch.


About the Instructor ✒️

I am an artificial intelligence specialist instructor who has been teaching Python and AI for 5 years.

The following courses are available on Inflearn.


Recommended for
these people

Who is this course right for?

  • Someone who can code in Python

  • Those with basic knowledge of deep learning

  • Those who want to understand the principles of reinforcement learning

Need to know before starting?

  • Python language

  • Basic knowledge of deep learning

Hello
This is YoungJea Oh

Career Verified

5,900

Learners

524

Reviews

163

Answers

4.8

Rating

23

Courses

I am an AI specialist instructor teaching Artificial Intelligence and Python based on over 30 years of IT field experience. I develop and teach practical-oriented curricula, including deep learning, NLP, LLM fine-tuning, LangChain/LangGraph-based AI agents, and AI-driven development (AIDD). I translate more than 30 years of development and operations experience gained at Hyundai Engineering & Construction's IT department, Samsung SDS, and Citibank Korea into realistic, hands-on lectures. Currently, I am conducting AI courses at institutions such as KOSA, KOSTA, and KITRI.

Homepage Address: https://ironmanciti.github.io/

More

Curriculum

All

87 lectures ∙ (18hr 58min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

38 reviews

4.7

38 reviews

  • tkpark7556님의 프로필 이미지
    tkpark7556

    Reviews 10

    ∙

    Average Rating 5.0

    5

    31% enrolled

    Thank you for explaining information about a new field to me in an easy-to-understand way.

    • nkhwi님의 프로필 이미지
      nkhwi

      Reviews 23

      ∙

      Average Rating 4.5

      5

      31% enrolled

      It's quite difficult, but I'm learning a lot because the explanations are more detailed compared to other lectures. I think it's the best lecture in the country.

      • trimurti
        Instructor

        Thank you for the great review.

    • okputto3340님의 프로필 이미지
      okputto3340

      Reviews 1

      ∙

      Average Rating 5.0

      5

      61% enrolled

      I was having trouble with reinforcement learning and was looking for related resources, and I think I've finally understood it well enough thanks to this lecture. I was especially satisfied with the two-step explanation for the practical exercises (flow, actual coding), and the debugging explanations of intermediate values were also very helpful. Thank you.

      • trimurti
        Instructor

        Thank you for the positive feedback.

    • kti14524912님의 프로필 이미지
      kti14524912

      Reviews 6

      ∙

      Average Rating 5.0

      5

      100% enrolled

      It’s great that I can neatly organize reinforcement learning theory and internalize it through hands-on practice implementing actual code!

      • kimdoohan님의 프로필 이미지
        kimdoohan

        Reviews 2

        ∙

        Average Rating 5.0

        Edited

        5

        100% enrolled

        The Only Korean-Language Course with “Just the Right Mix of Theory and Practice” Pros 1. It doesn’t get bogged down in deriving equations from the start. Instead, it explains concepts using a reasonable amount of math and then moves straight into implementation, which makes it easy to put what you’ve learned into practice. 2. It pairs extremely well with Hyukpenheim’s reinforcement learning theory lectures on YouTube, some of which are paid. 3. Courses that are suitable for beginners in reinforcement learning are very rare. They tend to offer either theory alone or code without much explanation. In that sense, this course—with its balanced mix of theory and implementation—was personally the most helpful. I took three courses: the KOCW open course, Hyukpenheim’s theory lectures, and this one, and this was the best. Cons The policy-based section only goes as far as REINFORCE. It would be perfect if it covered Actor-Critic, A2C, DDPG, and PPO as well. However, once you understand the general policy gradient formula and learn REINFORCE as an example, the other algorithms are only minor variations, so I think it should be entirely possible to find resources and implement them on your own using what you learned in the course. Thank you. I learned a lot. This was the only proper Korean-language reinforcement learning course that included both theory and practice. I felt lost after watching theory-only courses, but after taking this one, I think I’ll be able to study and implement individual algorithm papers on my own.

        YoungJea Oh's other courses

        Check out other courses by the instructor!

        Similar courses

        Explore other courses in the same field!

        25% off for new members

        $32.90

        25%

        $42.90