GraphCanon updated 2w · GitHub synced 2w
Decision brief
L2R is an open-source platform for reinforcement learning in autonomous racing simulators.
Good fit when
- When your project includes developing AI systems for autonomous vehicle simulation with a focus on racing environments
- For researchers needing a validated environment showcased at major AI conferences like ICCV and IJCAI
Avoid when
- When your project does not involve autonomous driving or is not specifically focused on the simulation of racing scenarios
- For those who cannot meet the hardware requirements, such as lacking a suitable Nvidia GPU for running the simulator
- Requirements:
- Requires Docker; Requires Python 3.8 or higher; Nvidia graphics card and associated drives are necessary, with minimum recommendation of an Nvidia 970 GTX for simulator operation; Installation assumes a Linux operating system. For non-Linux environments, a public cloud instance with GPU is suggested
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (954d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- 118 low (118 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install l2rSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
An open-source toolset for developing AI systems in the context of autonomous racing via reinforcement learning techniques.
Capability facts
- Deploy
- Self-host
Source: dockerfile:docker-compose.yml · Aug 1, 2026
- Docker
- Dockerfile present
Source: dockerfile:docker-compose.yml · Aug 1, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 1, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 1, 2026)
**Python:** We use Learn-to-Race with Python 3.8+.Source link
Tags
README
Requirements
Python: We use Learn-to-Race with Python 3.8+.
Graphics Hardware: An Nvidia graphics card & associated drives is required. An Nvidia 970 GTX graphics card is minimally sufficient to simply run the simulator, but a better card is recommended.
Docker: Commonly, the racing simulator runs in a Docker container.
Container GPU Access: If running the simulator in a container, the container needs access to the GPU, so nvidia-container-runtime is also required.
Installation
Due to the container GPU access requirement, this installation assumes a Linux operating system. If you do not have a Linux OS, we recommend running Learn-to-Race on a public cloud instance that has a sufficient GPU.
- Request access to the Racing simulator: https://www.aicrowd.com/challenges/learn-to-race-autonomous-racing-virtual-challenge
We recommmend running the simulator as a Python subprocess which simply requires that you specify the path of the simulator in the env_kwargs.controller_kwargs.sim_path of your configuration file. Alternatively, you can run the simulator as a Docker container by setting env_kwargs.controller_kwargs.start_container to True. If you prefer the latter, you can load the docker image as follows:
$ docker load < arrival-sim-image.tar.gz
- Download the source code from this repository and install the package requirements. We recommend using a virtual environment:
$ conda create -n l2r python=3.6
$ conda activate # activate the environment
(l2r) $ pip3 install git+https://github.com/learn-to-race/l2r.git@aicrowd-environment
For agents
This page has a .md twin and JSON over the API.