Reinforcement learning with AWS DeepRacer

WHAT WE ARE WORKING TOWARDS

AWS Deepracer is a fun way to learn and implement Machine learning with hands on experience. Developers of all skill levels can get hands on with machine learning through a cloud based 3D racing simulator, which they can start using simply by logging into their aws account. AWS DeepRacer is based on the model of reinforcement learning (RL). RL is an advanced machine learning (ML) technique that takes a very different approach to training models than other machine learning methods.

WHAT AWS DEEPRACER SERVICES PROVIDE

The user can now use the AWS DeepRacer 3D racing simulator. Experiment with multiple sensor inputs, the latest reinforcement learning algorithms, neural network configurations and simulation to-real domain transfer methods.

HOW TO BEGIN

You will first need to create your own deepracer car by selecting the type of car, the skin you want on it, the track you want it to run on. And finally, you can train your model by setting the time you want it to train for and then testing it! As you progress you can participate in the AWS League.It is a global autonomous racing league, driven by machine learning.There are 3 stages that you can advance to :-

1. Start in the Open Division and win virtual cars
2. Advance to the Pro Division and win gear
3. Take on the League's best and win a DeepRacer It is a fun community of many Machine learning Enthusiast and you can meet many new people thorugh the various community driven events.

CONCLUSION

Here are some of the official AWS links from their website containing various resources from where you can learn to build your own models and tracks. You can also improve your racing performance.

That's it, I hope I was able to spark some interest into you. Now it's time to get your hands dirty! All the best!