Bounded Regret for Finite-Armed Structured Bandits
Bounded Regret for Finite-Armed Structured Bandits
复制标题
DOI:
--
复制
发表时间:
2014-11
期刊:
影响因子:
--
通讯作者:
Tor Lattimore;R. Munos
中科院分区:
文献类型:
--
作者:
Tor Lattimore;R. Munos
We study a new type of K-armed bandit problem where the expected return of one arm may depend on the returns of other arms. We present a new algorithm for this general class of problems and show that under certain circumstances it is possible to achieve finite expected cumulative regret. We also give problem-dependent lower bounds on the cumulative regret showing that at least in special cases the new algorithm is nearly optimal.