Corpus ID: 225103209

Multitask Bandit Learning through Heterogeneous Feedback Aggregation

@article{Wang2020MultitaskBL,
  title={Multitask Bandit Learning through Heterogeneous Feedback Aggregation},
  author={Zongguo Wang and Chicheng Zhang and M. Singh and L. Riek and K. Chaudhuri},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.15390}
}
  • Zongguo Wang, Chicheng Zhang, +2 authors K. Chaudhuri
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol. We formulate this problem as the $\epsilon$-multi-player multi-armed bandit problem, in which a set of players concurrently interact with a set of arms, and for each arm, the reward distributions for all players are similar but not necessarily identical. We develop an upper confidence bound-based algorithm, RobustAgg$(\epsilon)$, that… CONTINUE READING

    Figures from this paper

    References

    SHOWING 1-10 OF 76 REFERENCES
    Multi-armed bandits in multi-agent networks
    • 25
    • PDF
    Distributed Learning in Multi-Armed Bandit With Multiple Players
    • K. Liu, Qing Zhao
    • Computer Science, Mathematics
    • IEEE Transactions on Signal Processing
    • 2010
    • 343
    • PDF
    Decentralized Learning for Multiplayer Multiarmed Bandits
    • 128
    • PDF
    My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player Bandits
    • 2
    • Highly Influential
    • PDF
    Social Learning in Multi Agent Multi Armed Bandits
    • 14
    • PDF
    Kernel Methods for Cooperative Contextual Bandits
    • 2
    • Highly Influential
    • PDF
    Optimal Algorithms for Multiplayer Multi-Armed Bandits
    • 6
    • Highly Influential
    • PDF
    Collaborative learning of stochastic bandits over a social network
    • 23
    • PDF
    Multi-Task Learning for Contextual Bandits
    • 27
    • PDF
    Distributed Multi-agent Multi-armed Bandits
    • 3
    • PDF