Corpus ID: 35869294

Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control

@article{Wu2017FlowAA,
  title={Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control},
  author={Cathy Wu and Aboudy Kreidieh and Kanaad Parvate and Eugene Vinitsky and A. Bayen},
  journal={ArXiv},
  year={2017},
  volume={abs/1710.05465}
}
Flow is a new computational framework, built to support a key need triggered by the rapid growth of autonomy in ground traffic: controllers for autonomous vehicles in the presence of complex nonlinear dynamics in traffic. Leveraging recent advances in deep Reinforcement Learning (RL), Flow enables the use of RL methods such as policy gradient for traffic control and enables benchmarking the performance of classical (including hand-designed) controllers with learned policies (control laws). Flow… Expand
Flow: Deep Reinforcement Learning for Control in SUMO
Flow: Open Source Reinforcement Learning for Traffic Control
Mixed-Autonomy Traffic Control with Proximal Policy Optimization
Simulation to scaled city: zero-shot policy transfer for traffic control via autonomous vehicles
Lagrangian Control through Deep-RL: Applications to Bottleneck Decongestion
Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures
Large-scale traffic control using autonomous vehicles and decentralized deep reinforcement learning
Hierarchical Joint Control for Urban Mixed-Autonomy Traffic Optimization
  • Jia Wu, Z. Li
  • Computer Science
  • 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI)
  • 2020
Adaptive Coordination Offsets for Signalized Arterial Intersections using Deep Reinforcement Learning
Hierarchical Regional Control for Traffic Grid Signal Optimization
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 119 REFERENCES
Framework for control and deep reinforcement learning in traffic
Emergent Behaviors in Mixed-Autonomy Traffic
Lagrangian Control through Deep-RL: Applications to Bottleneck Decongestion
Expert Level Control of Ramp Metering Based on Multi-Task Deep Reinforcement Learning
Dissipating stop-and-go waves in closed and open networks via deep reinforcement learning
Benchmarking Deep Reinforcement Learning for Continuous Control
End to End Learning for Self-Driving Cars
...
1
2
3
4
5
...