AWS DeepRacer is one of the fastest and most accessible ways to get started with Machine Learning. After just a single experience on the virtual track, you can begin to understand the fundamentals of Reinforcement Learning and start training models for autonomous vehicles.

In this session, we’ll share the most useful tips & tricks to help you progress in model training, from the basics to more advanced tools.

We’ll explore basic training models and explain the most common parameters and hyperparameters in AWS DeepRacer.

You’ll also learn how to use DeepRacer for Cloud (DRFC), a community-driven solution that enables professional-level training with SPOT instances and GPU support, significantly lowering training costs.

Finally, we’ll visually analyze logs and performance metrics to identify opportunities for improving your models.

Get started with AWS DeepRacer and Reinforcement Learning. Learn key tips, training strategies, and how to optimize costs using DRFC with SPOT instances and GPU—plus how to analyze performance to improve your models.