flow-project/flow

Health v2 · maintenance only

Adoption not part of the score

1188 stars · 395 forks observed · 2026-08-28

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

Flow is a computational framework for deep reinforcement learning and control experiments in traffic microsimulation, built on top of the SUMO simulator. It provides benchmarks and tools for studying mixed-autonomy traffic scenarios such as vehicle control and traffic flow optimization.

Use cases

• train reinforcement learning agents to control traffic flow
• benchmark RL algorithms on traffic control tasks
• simulate mixed-autonomy traffic with SUMO
• research autonomous vehicle control in traffic
• run traffic microsimulation experiments for academic papers
• study ramp metering and intersection control with RL

When to choose

• you need RL environments for traffic control research
• you want reproducible benchmarks for mixed-autonomy traffic
• you need to couple deep RL libraries with the SUMO traffic simulator

When to avoid

• you need general-purpose robotics or game RL environments unrelated to traffic
• you need a production traffic management system rather than a research framework
• you require active commercial support or frequent updates

Facets

framework · maturity maintenance

reinforcement-learning simulation benchmarking machine-learning reinforcement-learning autonomous-vehicles simulation machine-learning python traffic-microsimulation sumo mixed-autonomy-traffic deep-rl traffic-control benchmark-suite research linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="flow-project/flow")