Multi-agent meta-reinforcement learning based on contrastive predictive coding—For rapid adaptive traffic control after emergencies
Wei Jiang, Xianwei Huang, Genjie Wang, Ruting Li, Shanshan Tang · 2026
Read Multi-agent meta-reinforcement learning based on contrastive predictive coding—For rapid adaptive traffic control after emergencies by Wei Jiang, Xianwei Huang, Genjie Wang, Ruting Li, Shanshan Tang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13552721.txt.
Description
Wei Jiang and co-authors built emergency-aware traffic control in two thousand twenty-six. Emergency vehicles must cross junctions fast without gridlocking others. Many controllers rely on hand-designed traffic features. New emergency patterns often force slow retraining. The team combined meta-learning with a coding method for traffic states. The coder compresses long traffic streams into compact codes.
Intersection agents share coded views of nearby traffic. Messages are weighted by distance and delay. A priority layer adjusts signals by emergency severity. Few examples suffice for the policy to adapt. Tests ran on a standard traffic simulation platform. Scenarios used an emergency-focused city network model. The system cleared emergency routes with less side delay. Such control could aid cities after crashes or disasters.
Catalog record
| CREATOR | Wei Jiang, Xianwei Huang, Genjie Wang, Ruting Li, Shanshan Tang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |