gym-donkeycar
- Software
- Cars
- Simulator
A Gymnasium reinforcement-learning environment wrapper that lets agents drive simulated Donkey Car robots on several race tracks through the Donkey simulator.
Source on GitHub: github.com/tawnkramer/gym-donkeycar (opens in a new tab). Facts read at commit a1f4ca6 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit a1f4ca6 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Provides Gymnasium environments such as donkey-generated-track-v0 and donkey-warren-track-v0 for driving a simulated car.
- Actions are two values: steering and throttle, passed as a numpy array.
- Each step returns a reward combining game over, distance from the center line and speed, plus info such as cross-track error, speed and lap time.
- Can launch the simulator executable itself via a config, or connect to an already running simulator on a port.
- Offers ten environments, including warehouse, generated roads, Sparkfun AVC, Waveshare and Thunderhill tracks.
Written by Robotheca from the project's README (opens in a new tab) at commit a1f4ca6.
Getting started
- Difficulty
- Beginner
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 1 Mar 2026 on master
- Latest release
- Race Edition v25.10.06 (6 Oct 2025)
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.