BibTeX record journals/corr/abs-2411-00339

• > Home > journals/corr/abs-2411-00339

@article{DBLP:journals/corr/abs-2411-00339,
  author       = {Nobuaki Kikkawa and
                  Hiroshi Ohno},
  title        = {Unified theory of upper confidence bound policies for bandit problems
                  targeting total reward, maximal reward, and more},
  journal      = {CoRR},
  volume       = {abs/2411.00339},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2411.00339},
  doi          = {10.48550/ARXIV.2411.00339},
  eprinttype    = {arXiv},
  eprint       = {2411.00339},
  timestamp    = {Wed, 01 Jan 2025 14:15:42 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2411-00339.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}