RL Series-Implementation in PyTorch

Isaac Kargar
Nov 7 · 2 min read

I decided to implement different Reinforcement Learning algorithms in PyTorch. I try to do it as simple as possible for learning purposes. Here is a list of the algorithms that I hope I can implement: (I try to select the correct name for different techniques as much as I can)

Maybe I try a technique on several environments or several techniques on an environment. I also hope that I can implement some model-based RL and multi-agent RL techniques too. I will work on self-driving cars and RL in my PhD and will try to test some of these techniques in some environments such as CARLA or CarRacing gym env.

There are a lot of good resources to learn about RL that I will use and you can find some of them here:

And many more resources that you can find through the internet.

I reviewed these resources through the #100DaysOfMLCode challenge, the RL course at Aalto University and the studies that I’m doing for my PhD. I think that’s it for this post. We will continue with DQN in the next post.

Isaac Kargar

Written by

I’m a Ph.D. student at the Intelligent Robotics Group at Aalto University working on self-driving cars, reinforcement learning, and machine learning.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade