How a self driving car works?
A journey to learn reinforcement learning.
JML x AWS DeepRacer Bootcamp Pt. 1
You’ve probably have heard about self driving car. Maybe you’ve ever wondered how could it be possible. If you want to know some, than let’s deep dive into this article.
There are of course lots of parts that make autonomous driving can happens and it is still growing. One technology that make this self-driving car possible is the rise of computing technology using one of artificial intelligence (AI) technology which is reinforcement learning (RL).
So what is artificial intelligence? Is it like in Terminator movie? And what is reinforcement learning?
JML x AWS DeepRacer Bootcamp
So recently I was selected by Jakarta Machine Learning (JML) and AWS to join DeepRacer Bootcamp. Big thanks to JML and AWS for giving me this opportunity. So this is around 3 months bootcamp with 9 participants where we are mentored by Senior Developer Advocate from AWS to learn Reinforcement Learning and AWS DeepRacer. So, I would to share my journy on learning reinforcement learning in this bootcamp with you. In this article I will talk a bit on introduction about Reinforcement Learning and AWS DeepRacer. Later on, I will go deeply on both topics.
Reinforcement Learning
I have said before about Artificial Intelligence. In a brief explanation, artificial intelligence is where the machine can learn by itself and reinforcement learning is part of it.
Have you train a pet or heard about training a pet? When we train a pet we give set of instruction to follow, our pet will act on that command, if it is right we give it reward, and punishment if wrong. The pet will learn from experience what it should do to get more reward and avoid punishment. This type of learning is what we try to mimic in reinforcement learning. Taking this analogous, the pet is called an agent. It will explore the environment and do some action. Based on its action it will be given reward, the reward is either positive or negative. The goal of the agent is to get as many positive reward as possible.
AWS DeepRacer
So before we try to implement our model on real car, which can be dangerous and cost a lot. AWS gives us opportunity to implement and also learn reinforcement learning at fly. Then we also have AWS DeepRacer league where we can race with others. Here is the AWS DeepRacer definition from its website.
Get hands-on with a fully autonomous 1/18th scale race car driven by reinforcement learning, 3D racing simulator, and global racing league.
That’s all for now. On the next article I will go deeper on the math behind Reinforcement Learning, also on how to create our first reinforcement learning model in AWS DeepRacer, and lot other interesting topic as I continue my JML x AWS Bootcamp.
