Dimensions overall score 3.0

GitHub Code Pulse

No public code linked for this paper yet.

• Centralized, fully decentralized, and parameter-sharing decentralized RL controllers were trained and evaluated for urban corridor traffic networks.method 95%
• RL controllers were compared with a classical baseline MaxPressure controller in terms of capacity regions and average travel times (ATTs).result 95%
• The parameter-sharing controller can be generalized to be deployed on larger networks than it was originally trained on.technical 90%
• Traffic may self-organize into 'green waves' even when junctions are not formally coordinated.result 85%
• The study extends systematic capacity region perspective to multi-junction traffic networks.method 90%
• The research focuses specifically on the special case of urban corridor networks.method 95%
• The study provides systematic analyses of reinforcement learning controllers in signalized urban corridors.method 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card