Reinforcement Learning for Mixed Autonomy Intersections
This work addresses traffic management for mixed autonomy systems, showing incremental improvements in coordination without explicit reward shaping.
The paper tackled the problem of controlling mixed autonomy traffic at intersections using a model-free reinforcement learning method, achieving near-optimal throughput with 33-50% controlled vehicles and demonstrating generalization across different traffic conditions.
We propose a model-free reinforcement learning method for controlling mixed autonomy traffic in simulated traffic networks with through-traffic-only two-way and four-way intersections. Our method utilizes multi-agent policy decomposition which allows decentralized control based on local observations for an arbitrary number of controlled vehicles. We demonstrate that, even without reward shaping, reinforcement learning learns to coordinate the vehicles to exhibit traffic signal-like behaviors, achieving near-optimal throughput with 33-50% controlled vehicles. With the help of multi-task learning and transfer learning, we show that this behavior generalizes across inflow rates and size of the traffic network. Our code, models, and videos of results are available at https://github.com/ZhongxiaYan/mixed_autonomy_intersections.