@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{AAMAS21-cui,
  author = {Jiaxun Cui and William Macke and Harel Yedidsion and Aastha Goyal and Daniel Urieli and Peter Stone},
  title = {Scalable Multiagent Driving Policies For Reducing Traffic Congestion},
  booktitle = {Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
  location = {Virtual},
  month = {May},
  year = {2021},
  abstract = {
              Traffic congestion is a major challenge in modern urban
              settings.  The industry-wide development of autonomous
              and automated vehicles (AVs) motivates the question of
              how can AVs contribute to congestion reduction. Past
              research has shown that in small scale mixed traffic
              scenarios with both AVs and human-driven vehicles, a
              small fraction of AVs executing a controlled multiagent
              driving policy can mitigate congestion. In this paper,
              we scale up existing approaches and develop new
              multiagent driving policies for AVs in scenarios with
              greater complexity. We start by showing that a
              congestion metric used by past research is manipulable
              in open road network scenarios where vehicles
              dynamically join and leave the road. We then propose
              using a different metric that is robust to manipulation
              and reflects open network traffic efficiency. Next, we
              propose a modular transfer reinforcement learning
              approach, and use it to scale up a multiagent driving
              policy to outperform human-like traffic and existing
              approaches in a simulated realistic scenario, which is
              an order of magnitude larger than past scenarios
              (hundreds instead of tens of vehicles). Additionally,
              our modular transfer learning approach saves up to 80%
              of the training time in our experiments, by focusing its
              data collection on key locations in the
              network. Finally, we show for the first time a
              distributed multiagent policy that improves congestion
              over human-driven traffic. The distributed approach is
              more realistic and practical, as it relies solely on
              existing sensing and actuation capabilities, and does
              not require adding new communication infrastructure.
  },
  wwwnote={<a href="https://www.cs.utexas.edu/~aim/flow.html" target="_blank">Project page, with videos</a>},
}