The Impact of Batch Learning in Stochastic Linear Bandits. (arXiv:2202.06657v2 [cs.LG] UPDATED)

We consider a special case of bandit problems, named batched bandits, in
which an agent observes batches of responses over a certain time period. Unlike
previous work, we consider a more practically relevant batch-centric scenario
of batch learning. That is to say, we provide a policy-agnostic regret analysis
and demonstrate upper and lower bounds for the regret of a candidate policy.
Our main theoretical results show that the impact of batch learning is a
multiplicative factor of batch size relative …

arxiv impact learning linear stochastic