Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs.

Tianyuan Jin Hao-Lun Hsu William Chang Pan Xu

Published in: AAAI (2024)

Keyphrases

multi agent
multi armed bandit
regret bounds
reinforcement learning
high dimensional
random sampling
sampling algorithm
sparse representation
linear regression
regularized least squares
lower bound
markov chain monte carlo
linear predictors