Park: An Open Platform for Learning Augmented Computer Systems
Abstract
This paper presents Park, an open extensible platform that uses a common interface to connect to a suite of real world computer systems for RL augmented optimizations. These systems cover a wide spectrum of problems, including both global vs. distributed control, and fast control loop vs. long term planning. This dataset unveils unique challenges that the existing off-the-shelf RL techniques cannot solve. The challenges occur in the representation and search of the state-action space, the special property of the decision process and the reality gap between simulations and actual systems. To understand the effect of these challenges, we benchmark several existing RL algorithms in Park with comparing heuristic baselines.
Cite
Text
Mao et al. "Park: An Open Platform for Learning Augmented Computer Systems." ICML 2019 Workshops: RL4RealLife, 2019.Markdown
[Mao et al. "Park: An Open Platform for Learning Augmented Computer Systems." ICML 2019 Workshops: RL4RealLife, 2019.](https://mlanthology.org/icmlw/2019/mao2019icmlw-park/)BibTeX
@inproceedings{mao2019icmlw-park,
title = {{Park: An Open Platform for Learning Augmented Computer Systems}},
author = {Mao, Hongzi and Negi, Parimarjan and Narayan, Akshay and Wang, Hanrui and Yang, Jiacheng and Wang, Haonan and Marcus, Ryan and Addanki, Ravichandra and Khani, Mehrdad and He, Songtao and Nathan, Vikram and Cangialosi, Frank and Venkatakrishnan, Shaileshh Bojja and Weng, Wei-Hung and Han, Song and Kraska, Tim and Alizadeh, Mohammad},
booktitle = {ICML 2019 Workshops: RL4RealLife},
year = {2019},
url = {https://mlanthology.org/icmlw/2019/mao2019icmlw-park/}
}