Around re:Invent 2024, AWS announced that the DeepRacer service would be decommissioned on December 15, 2025, and that a new solution would be available by then to allow individuals and organizations to deploy DeepRacer into their own AWS accounts. December 15 came and went, and no solution was in sight. But in late January the new DeepRacer on AWS solution launched, and is available in the AWS Solutions Library!
The Solution
What is this Solution anyway?
Since its launch in 2018, AWS DeepRacer was a Service. AWS Services are the foundational components of AWS (like S3, EC2, CloudWatch, etc.) and are managed through the AWS Console or CLI. They typically don’t provide end‑user functionality. DeepRacer was different: It was an end‑user product hosted in the AWS Console, built on top of services like SageMaker, RoboMaker, Lambda, S3, CloudWatch, Kinesis, and others.
A major pain point with the DeepRacer service was that every racer needed AWS Console access. For individuals this wasn’t a big issue, but for larger corporate events it was a nightmare. Integration with corporate identity and access management was possible, but cumbersome for both admins and racers.
A Solution, in contrast, is an application provided by AWS that you deploy into your own AWS account. You can run it as‑is or modify it because the source code is available. Best of all, it typically provides a normal website with user access managed by Cognito.
What does it mean for me?
To use the new Solution you need to install it into your own AWS account! I already wrote a blog post outlining your options for installation, including an initial review.
A wake-up call
The launch of the Solution was a bit of a wake-up call. Seeing that there was a future for DeepRacer made community contributors wake up and bring several components back up to speed.
DeepRacer-for-Cloud & DeepRacer Simulation
The twin community repositories DeepRacer-for-Cloud and Deepracer-Simapp had seen little love since re:Invent 2024, but with DeepRacer-on-AWS providing a ROS2 based simulation it was time to upgrade!
The combined solution – where DRfC provides the front-end for local or EC2 instance training, and the Simapp provides the backend simulation environment and training logic – has been upgraded, porting the community enhancements to the new ROS2 stack!
DeepRacer Analysis Notebooks and Python Utilities
The DeepRacer Analysis Notebooks and the underlying DeepRacer Utilities Python library also received an upgrade.
- Support for DRoA log archives: The log files are similar, but the directory structure is not. Bonus: It is now possible to process a downloaded archive without opening it!
- Uses latest Jupyter and Python versions
- Creation of training performance statistics
- Improved graphics, including ability to animate training progress.
See the blog post DeepRacer on AWS: Analyzing Your Training Logs - 2026 Edition for more details on how to use the Notebooks together with DeepRacer on AWS.
DeepRacer Event Manager
The AWS-provided DeepRacer Event Manager has also received some attention – dependencies have been upgraded, along with several improvements that simplify deployment and reduce costs.
What is next?
The goal is clear: bring DeepRacer events back for everyone, from small local leagues to large corporate tournaments, powered by DeepRacer on AWS and DREM. Online community racing is also on the horizon — there are a few practical hurdles to clear around training costs, but we’re working on it.
DeepRacer is alive again, and the community is moving fast. Want to shape where it goes? Join us on Discord and make your voice heard!