A data-based online reinforcement learning algorithm satisfying probably approximately correct principle

Yuanheng Zhu, Dongbin Zhao

BibTeX
@article{zhu2015data,
  author = {Yuanheng Zhu and Dongbin Zhao},
  title = {{A data-based online reinforcement learning algorithm satisfying probably approximately correct principle}},
  journal = {Neural Computing and Applications},
  year = {2015},
  url = {https://openreview.net/forum?id=X-7TavW_F3G},
}

Loading related content...

Figure