Optimizing a Start-Stop Controller Using Policy Search

Noel Hollingsworth, Jason Meyer, Ryan McGee, Jeffrey Doering, George Dimitri Konidaris, Leslie Pack Kaelbling

AAAI 2014 pp. 2984-2989

doi:10.1609/AAAI.V28I2.19024 /aaai/2014/hollingsworth2014aaai-optimizing/

Abstract

We applied a policy search algorithm to the problem of optimizing a start-stop controller—a controller used in a car to turn off the vehicle’s engine, and thus save energy, when the vehicle comes to a temporary halt. We were able to improve the existing policy by approximately 12% using real driver trace data. We also experimented with using multiple policies, and found that doing so could lead to a further 8% improvement if we could determine which policy to apply at each stop. The driver’s behaviors before stopping were found to be uncorrelated with the policy that performed best; however, further experimentation showed that the driver’s behavior during the stop may be more useful, suggesting a useful direction for adding complexity to the underlying start-stop policy.

AAAI Semantic Scholar

Cite

Text

Hollingsworth et al. "Optimizing a Start-Stop Controller Using Policy Search." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I2.19024

Markdown

[Hollingsworth et al. "Optimizing a Start-Stop Controller Using Policy Search." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/hollingsworth2014aaai-optimizing/) doi:10.1609/AAAI.V28I2.19024

BibTeX

@inproceedings{hollingsworth2014aaai-optimizing,
  title     = {{Optimizing a Start-Stop Controller Using Policy Search}},
  author    = {Hollingsworth, Noel and Meyer, Jason and McGee, Ryan and Doering, Jeffrey and Konidaris, George Dimitri and Kaelbling, Leslie Pack},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2014},
  pages     = {2984-2989},
  doi       = {10.1609/AAAI.V28I2.19024},
  url       = {https://mlanthology.org/aaai/2014/hollingsworth2014aaai-optimizing/}
}