RL

1. Why RL all of sudden?

I am 39 years old now.

I started my career as an LTE/5G modem protocol engineer and later became a full-stack software engineer building distributed product systems.

Recently, I was assigned to work on reinforcement learning (RL). To be honest, I wasn’t particularly excited about it at first because it isn’t my area of expertise.

Then I remembered how my career had progressed in the past.

When I was a junior engineer, I often found myself working on things I hadn’t planned for. Complaining never changed anything, so I learned to keep my head down, do my best, and keep moving forward.

LTE and 5G were areas that I had to spend years learning, even though I wasn’t especially passionate about them in the beginning.

Now RL is the next chapter.

I’ll try to find the fun in it. Besides, I had already been thinking about moving to an ML-related team around the time of the reorganization. Machine learning is one of the most exciting fields today, and I’ve always been curious about it.

2. What I am going to do?

I’ve been trying to learn machine learning for a long time.

Back then, machine learning was already popular, but web development was even more popular.

Like many people, I took online courses, read books, and learned the fundamentals. Unfortunately, I kept forgetting what I had learned because I never had the chance to apply it in real work.

This time, I’d like to revisit the fundamentals from the beginning.

While I’ll briefly cover general machine learning concepts, this blog will mainly focus on reinforcement learning.

3. How are you going to learn these stuffs?

My goal is to build a solid understanding of the fundamentals by writing about what I learn.

I also hope this journey eventually leads to building a small RL toy project.

Here are the resources I’ll be using:

• MATLAB Tech Talks: https://youtu.be/pc-H4vyg2L4?si=Ag0p2FTLIr1qL1Hm

• Hyukpen’s Reinforcement Learning Series: https://youtu.be/cvctS4xWSaU?si=mB4P2zB-vnzLr11z

I’ll probably add more resources as I continue learning.

4. Plans

Here’s my plan:

Learn the core ideas behind reinforcement learning. Come up with a project idea. Build it. Share what I learn along the way.

I’ll write posts based on my understanding rather than simply summarizing what I read or watch.

As for the project, I’ll keep thinking until I find something interesting enough to build. Once I do, I’ll share that journey here as well.

5. So, what is this post about?

It’s simply my way of throwing my hat into the ring.

I’m officially stepping into the world of machine learning.

See you in the next post.