huawei-noah/SMARTS

Health v2 · maintenance only

Adoption not part of the score

1134 stars · 220 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

simulation reinforcement-learning machine-learning autonomous-vehicles reinforcement-learning simulation machine-learning python cross-platform multi-agent-rl autonomous-driving simulator research traffic-scenarios linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="huawei-noah/SMARTS")