# aws-solutions-library-samples/guidance-for-training-an-aws-deepracer-model-using-amazon-sagemaker

DeepRacer workshop content. This Guidance demonstrates how software developers can use an Amazon SageMaker Notebook instance to directly train and evaluate AWS DeepRacer models with full control

Repository: https://github.com/aws-solutions-library-samples/guidance-for-training-an-aws-deepracer-model-using-amazon-sagemaker
Canonical: https://ross.abutalabs.com/products/guidance-for-training-an-aws-deepracer-model-using-amazon-sagemaker
Homepage: https://aws.amazon.com/solutions/guidance/training-an-aws-deepracer-model-using-amazon-sagemaker/
Language: Jupyter Notebook
License: MIT-0
License Family: permissive
Last push: 2024-10-21T01:59:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2840, "days_push": 682, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1245, forks 703 (observed 2026-08-28T04:04:07.044398+00:00)

## What it is
AWS Solutions Library guidance providing Jupyter Notebook workshop content for training and evaluating AWS DeepRacer reinforcement learning models directly on Amazon SageMaker. It gives developers full control over the simulation environment, neural network inputs and architecture, distributed rollouts, and debugging beyond what the DeepRacer console offers.

## Use cases
- train a DeepRacer model with SageMaker instead of the console
- customize the neural network architecture for a DeepRacer racer
- modify the DeepRacer simulation environment and reward function
- run distributed rollouts for reinforcement learning training
- learn reinforcement learning hands-on with AWS services
- debug and evaluate DeepRacer models in RoboMaker simulation
- estimate and manage AWS costs for RL model training

## When to choose
- you already know AWS DeepRacer and want deeper control over training
- you want to tune neural network inputs, architecture, or simulation for racing
- you are running a workshop or self-paced learning on RL with SageMaker and RoboMaker

## When to avoid
- you are brand new to machine learning and want the simplest DeepRacer experience (use the DeepRacer console)
- you need a production ML pipeline rather than workshop-style notebooks
- you cannot use the US East (N. Virginia) region or want to avoid ongoing AWS costs

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, reinforcement-learning, simulation, developer-tools
- domain: machine-learning, reinforcement-learning, cloud-computing, tutorials, developer-tools
- platform: python, cloud
- tags: aws-deepracer, sagemaker, robomaker, jupyter-notebooks, aws-guidance, workshop, reinforcement-learning-training, autonomous-racing, docker

## Member repositories
- aws-solutions-library-samples/guidance-for-training-an-aws-deepracer-model-using-amazon-sagemaker (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:07.044398+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:08:08.110626+00:00, confidence not recorded.
  - readme: https://github.com/aws-solutions-library-samples/guidance-for-training-an-aws-deepracer-model-using-amazon-sagemaker (fetched 2026-08-28T04:04:07.044398+00:00, sha 3969758215b3)
  - homepage: https://aws.amazon.com/solutions/guidance/training-an-aws-deepracer-model-using-amazon-sagemaker/ (fetched 2026-08-29T12:19:49.635233+00:00, sha 38075419b4a5)
  - site_page: https://aws.amazon.com/getting-started?nc2=h_dsc_aa_gs (fetched 2026-08-29T12:19:49.641366+00:00, sha f35fd0664950)
  - site_page: https://aws.amazon.com/about-aws/global-infrastructure?nc2=h_dsc_aa_gi (fetched 2026-08-29T12:19:49.643415+00:00, sha 79a446e5fbd1)
  - site_page: https://aws.amazon.com/products/developer-tools/agent-toolkit-for-aws?nc2=h_dsc_ex_s5 (fetched 2026-08-29T12:19:49.639168+00:00, sha 3cc21b596f92)
  - site_page: https://aws.amazon.com/pricing?nc2=h_pr_hub (fetched 2026-08-29T12:19:49.645326+00:00, sha e2abd01d7981)
  - site_page: https://aws.amazon.com/savingsplans?nc2=h_pr_sp (fetched 2026-08-29T12:19:49.647124+00:00, sha 9ff3c7ad93e0)
  - site_page: https://aws.amazon.com/s3/pricing?nc2=h_pr_s3 (fetched 2026-08-29T12:19:49.649053+00:00, sha 97bbf99c3793)
  - site_page: https://aws.amazon.com/bedrock/pricing?nc2=h_pr_br (fetched 2026-08-29T12:19:49.652246+00:00, sha 4ccc538a3696)
  - site_page: https://aws.amazon.com/rds/pricing?nc2=h_pr_rds (fetched 2026-08-29T12:19:49.654053+00:00, sha 538280f30c8a)
- Data as of 2026-08-30T08:39:29.467469+00:00.