Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment
Researchers deployed 100 reinforcement learning (RL)-controlled cars into rush-hour highway traffic to smooth congestion and reduce fuel consumption. They tackled frustrating slowdowns and speedups by training efficient flow-smoothing controllers using fast, data-driven simulations that RL agents interact with, learning to maximize energy efficiency while maintaining throughput and operating safely around human drivers. The experiment demonstrated that a small proportion of well-controlled autonomous vehicles (AVs) can significantly improve traffic flow and fuel efficiency for all drivers, using controllers deployable on most modern vehicles with standard radar sensors, operating in a decentralized manner.