Environments¶
HighwayEnv includes the following ten environments for autonomous driving decision-making. Each environment features configurable observations, actions, dynamics, and rewards — see Configuring an environment for details.
Environment |
Description |
Action type |
|---|---|---|
Drive fast on a multilane highway while avoiding collisions. |
Discrete |
|
Merge onto a highway from an on-ramp through dense traffic. |
Discrete |
|
Navigate a roundabout with merging and exiting traffic. |
Discrete |
|
Park in a given space with the correct heading (goal-conditioned). |
Continuous |
|
Cross an unsignalized intersection among other vehicles. |
Discrete |
|
Follow a racetrack as fast as possible while staying on the road. |
Continuous |
|
Steer to follow a sine-wave lane using bicycle dynamics. |
Continuous |
|
Overtake on a two-way road with oncoming traffic (risk management). |
Discrete |
|
Navigate across lanes to reach a highway exit ramp. |
Discrete |
|
Overtake blocking vehicles through a double-lane U-turn. |
Discrete |
All environments follow the Gymnasium API and are highly configurable via arguments specified in each environment’s documentation.