The biobjective multiarmed bandit: learning approximate lexicographic optimal allocations

Cem TEKİN

Makale detayları

The biobjective multiarmed bandit: learning approximate lexicographic optimal allocations

Yazarlar:

Cem TEKİN

Yayıncı:

TUBITAK

Dergi:

Turkish Journal of Electrical Engineering and Computer Science 2019 Vol.27 Issue 2, pp.1065-1080

Belge Tipi:

Makale

Yayın Tarihi:

3/2019

Belge Dili:

Türkçe

Document ID (Org No.):

2000734107

Sıklık:

İki Aylık

eISSN:

1303-6203

pISSN:

1300-0632

Özet:

 

We consider a biobjective sequential decision-making problem where an allocation (arm) is called ϵϵ\epsilon lexicographic optimal if its expected reward in the first objective is at most ϵϵ\epsilon smaller than the highest expected reward, and its expected reward in the second objective is at least the expected reward of a lexicographic optimal arm. The goal of the learner is to select arms that are ϵϵ\epsilon lexicographic optimal as much as possible without knowing the arm reward distributions beforehand. For this problem, we first show that the learner's goal is equivalent to minimizing the ϵϵ\epsilon lexicographic regret, and then, propose a learning algorithm whose ϵϵ\epsilon lexicographic gap-dependent regret is bounded and gap-independent regret is sublinear in the number of rounds with high probability. Then, we apply the proposed model and algorithm for dynamic rate and channel selection in a cognitive radio network with imperfect channel sensing. Our results show that the proposed algorithm is able to learn the approximate lexicographic optimal rate--channel pair that simultaneously minimizes the primary user interference and maximizes the secondary user throughput.

Makale detayları

The biobjective multiarmed bandit: learning approximate lexicographic optimal allocations

Yazarlar: Cem TEKİN

Yayıncı: TUBITAK

Dergi: Turkish Journal of Electrical Engineering and Computer Science 2019 Vol.27 Issue 2, pp.1065-1080

Belge Tipi: Makale

Yayın Tarihi: 3/2019

Belge Dili: Türkçe

Document ID (Org No.): 2000734107

Sıklık: İki Aylık

eISSN: 1303-6203

pISSN: 1300-0632

Sayı

Yazarlar:

Cem TEKİN

Yayıncı:

TUBITAK

Dergi:

Turkish Journal of Electrical Engineering and Computer Science 2019 Vol.27 Issue 2, pp.1065-1080

Belge Tipi:

Makale

Yayın Tarihi:

3/2019

Belge Dili:

Türkçe

Document ID (Org No.):

2000734107

Sıklık:

İki Aylık

eISSN:

1303-6203

pISSN:

1300-0632