An episode of one of the environments available in HighwayEnv.

A collection of environments for autonomous driving and tactical decision-making tasks. Originally developed by Edouard Leurent and currently maintained by Jin Huang.

The documentation website is at highway-env.farama.org, and we have a public discord server (which we also use to coordinate development work) that you can join here: https://discord.gg/bnJ6kubTg6

Installation

To install HighwayEnv, use:

pip install highway-env

or with uv:

uv add highway-env          # adds to project dependencies and installs (preferred)
uv pip install highway-env  # or install without adding to a project (pip install)

We support Linux and macOS primarily, with Windows support maintained on a best-effort basis.

Environments

HighwayEnv includes 10 driving scenario families: highway, intersection, exit, lane-keeping, merge, parking, racetrack, roundabout, two-way, and u-turn, with several environments also offering fast, continuous-control, connected-lane, multi-agent, generic, large, or oval variants. The full list with descriptions and configuration options is available in the documentation.

Previews

highway
merge
roundabout
parking
intersection
racetrack
lane-keeping
two-way
exit
u-turn

Usage

import gymnasium as gym
import highway_env

gym.register_envs(highway_env)

# Initialise the environment
env = gym.make("highway-v0", config={"lanes_count": 3}, render_mode="human")

# Reset the environment to generate the first observation
obs, info = env.reset()
for _ in range(1000):
    # this is where you would insert your policy
    action = env.action_space.sample()

    # step (transition) through the environment with the action
    # receiving the next observation, reward and if the episode has terminated or truncated
    obs, reward, terminated, truncated, info = env.step(action)

    # If the episode has ended then we can reset to start a new episode
    if terminated or truncated:
        obs, info = env.reset()

env.close()

See the documentation for more examples including how to train agents with Stable Baselines3 and Google Colab notebooks. For examples of trained agents (DQN, DDPG, Value Iteration, MCTS), see the Agent Examples page.

Documentation

Read the documentation online.

Development Roadmap

Here is the roadmap for future development work.

Citating

If you use HighwayEnv in your work, please consider citing it with:

@misc{highway-env,
  author = {Leurent, Edouard},
  title = {An Environment for Autonomous Driving Decision-Making},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/Farama-Foundation/HighwayEnv}},
}

Publications

A list of publications using HighwayEnv can be found in the documentation.