# Farama-Foundation/HighwayEnv

A collection of environments for autonomous driving and tactical decision-making tasks

Repository: https://github.com/Farama-Foundation/HighwayEnv
Canonical: https://ross.abutalabs.com/products/highwayenv
Homepage: https://highway-env.farama.org/
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, autonomous-driving, gymnasium-environment
Last push: 2026-08-22T12:17:50+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 84, longevity 100
- inputs: {"age_days": 3213, "days_push": 11, "days_rel": 26, "gap_med": 57, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3298, forks 887 (observed 2026-08-28T04:07:55.649838+00:00)

## What it is
HighwayEnv is a collection of Gymnasium environments for autonomous driving and tactical decision-making tasks, covering scenarios like highway cruising, merging, intersections, parking, and racetracks. It offers configurable observations, actions, dynamics, and rewards, and is maintained under the Farama Foundation.

## Use cases
- train reinforcement learning agents for autonomous driving
- simulate highway merging and lane-change scenarios
- benchmark tactical decision-making policies
- prototype driving environments with custom rewards and dynamics
- study multi-agent driving behavior
- teach RL with lightweight driving simulators

## When to choose
- you need lightweight, fast Gymnasium driving environments for RL research or education
- you want configurable observations, actions, and rewards for driving tasks
- you need scenarios like intersections, roundabouts, parking, or racetracks without a full simulator

## When to avoid
- you need photorealistic rendering or full sensor simulation like CARLA
- you require high-fidelity vehicle physics or hardware-in-the-loop testing
- you need guaranteed Windows support, which is only best-effort

## Facets
- artifact type: library
- maturity: active
- function: reinforcement-learning, simulation, machine-learning
- domain: autonomous-vehicles, reinforcement-learning, simulation, machine-learning
- platform: python, windows
- tags: gymnasium, autonomous-driving, driving-simulator, decision-making, multi-agent, farama-foundation, linux, macos

## Member repositories
- Farama-Foundation/HighwayEnv (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:55.649838+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 2026-08-30T07:22:41.126053+00:00, confidence not recorded.
  - readme: https://github.com/Farama-Foundation/HighwayEnv (fetched 2026-08-28T04:07:55.649838+00:00, sha 67adbcbdbb07)
  - homepage: https://highway-env.farama.org/ (fetched 2026-08-29T09:35:39.693184+00:00, sha ccb9db17975f)
  - site_page: https://highway-env.farama.org/installation (fetched 2026-08-29T09:35:39.702467+00:00, sha 39e0f964072c)
  - site_page: https://highway-env.farama.org/quickstart (fetched 2026-08-29T09:35:39.704800+00:00, sha 789547107594)
  - site_page: https://highway-env.farama.org/environments/roundabout (fetched 2026-08-29T09:35:39.707129+00:00, sha 135e496f299b)
  - site_page: https://highway-env.farama.org/faq (fetched 2026-08-29T09:35:39.708992+00:00, sha c0bb2ccbf859)
- Data as of 2026-08-30T08:39:29.467469+00:00.