Residual Bootstrap Exploration for Stochastic Linear Bandit. (arXiv:2202.11474v2 [stat.ML] UPDATED)

Web: http://arxiv.org/abs/2202.11474

We propose a new bootstrap-based online algorithm for stochastic linear
bandit problems. The key idea is to adopt residual bootstrap exploration, in
which the agent estimates the next step reward by re-sampling the residuals of
mean reward estimate. Our algorithm, residual bootstrap exploration for
stochastic linear bandit (\texttt{LinReBoot}), estimates the linear reward from
its re-sampling distribution and pulls the arm with the highest reward
estimate. In particular, we contribute a theoretical framework to demystify
residual bootstrap-based exploration mechanisms in stochastic …

arxiv exploration linear ml stochastic