# huawei-noah/SMARTS

Scalable Multi-Agent RL Training School for Autonomous Driving

Repository: https://github.com/huawei-noah/SMARTS
Canonical: https://ross.abutalabs.com/products/smarts
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, python, autonomous-driving, simulator
Last push: 2025-01-31T23:17:16+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 4, release rhythm 8, longevity 100
- inputs: {"age_days": 2157, "days_push": 579, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1134, forks 220 (observed 2026-08-28T04:03:43.165345+00:00)

## What it is
SMARTS is a simulation platform for multi-agent reinforcement learning research focused on autonomous driving, emphasizing realistic and diverse agent interactions. It is part of Huawei Noah's Ark Lab's XingTian RL platform suite and is distributed on PyPI.

## Use cases
- train multi-agent RL policies for autonomous driving
- simulate realistic traffic interactions between vehicles
- benchmark driving agents in diverse scenarios
- research behavior of interacting autonomous vehicles
- integrate driving simulators with RL frameworks like XingTian

## When to choose
- you need a purpose-built driving simulator for multi-agent RL research
- you want realistic, diverse multi-agent traffic interactions
- you work in Python and want a pip-installable research platform

## When to avoid
- you need a production-grade autonomous driving stack rather than a research simulator
- you require single-agent-only simple gym environments with minimal setup
- you need heavy real-time rendering fidelity for game-like visuals

## Facets
- artifact type: library
- maturity: maintenance
- function: simulation, reinforcement-learning, machine-learning
- domain: autonomous-vehicles, reinforcement-learning, simulation, machine-learning
- platform: python, cross-platform
- tags: multi-agent-rl, autonomous-driving, simulator, research, traffic-scenarios, linux, macos

## Member repositories
- huawei-noah/SMARTS (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:43.165345+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 2026-08-30T06:37:06.274448+00:00, confidence not recorded.
  - readme: https://github.com/huawei-noah/SMARTS (fetched 2026-08-28T04:03:43.165345+00:00, sha b281a4ef6ae9)
  - registry_pypi: https://pypi.org/pypi/smarts/json (fetched 2026-08-29T12:42:05.687640+00:00, sha 4cde8bc3dfc4)
- Data as of 2026-08-30T08:39:29.467469+00:00.