Imitation Upper Confidence Bound for Bandits on a Graph

AAAI 2018 pp. 8113-8114

doi:10.1609/AAAI.V32I1.12183 /aaai/2018/lupu2018aaai-imitation/

Abstract

We consider a graph of interconnected agents implementing a common policy and each playing a bandit problem with identical reward distributions. We restrict the information propagated in the graph such that agents can uniquely observe each other's actions. We propose an extension of the Upper Confidence Bound (UCB) algorithm to this setting and empirically demonstrate that our solution improves the performance over UCB according to multiple metrics and within various graph configurations.

PDF AAAI Semantic Scholar

Cite

Text

Lupu and Precup. "Imitation Upper Confidence Bound for Bandits on a Graph." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12183

Markdown

[Lupu and Precup. "Imitation Upper Confidence Bound for Bandits on a Graph." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/lupu2018aaai-imitation/) doi:10.1609/AAAI.V32I1.12183

BibTeX

@inproceedings{lupu2018aaai-imitation,
  title     = {{Imitation Upper Confidence Bound for Bandits on a Graph}},
  author    = {Lupu, Andrei and Precup, Doina},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8113-8114},
  doi       = {10.1609/AAAI.V32I1.12183},
  url       = {https://mlanthology.org/aaai/2018/lupu2018aaai-imitation/}
}