2022
DOI: 10.48550/arxiv.2201.04805
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Non-Stationary Representation Learning in Sequential Linear Bandits

Abstract: In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the agent performs a series of tasks drawn from distinct sets associated with different environments. The embeddings of tasks in each set share a low-dimensional feature extractor called representation, and representations are different across sets. We propose an online algorithm that facilitates efficient decision-making by learning and tr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
2

Relationship

1
1

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 18 publications
0
3
0
Order By: Relevance
“…Meta-learning is closely related to representation learning, although the assumption is not the same [Denevi et al, 2019;Finn et al, 2019;Lee et al, 2019;Bertinetto et al, 2018]. There are also other works on different directions such linear MDP with a generative model [Lu et al, 2021], non-stationary sequential learning [Qin et al, 2022], and linear dynamical systems [Modi et al, 2021].…”
Section: Related Workmentioning
confidence: 99%
“…Meta-learning is closely related to representation learning, although the assumption is not the same [Denevi et al, 2019;Finn et al, 2019;Lee et al, 2019;Bertinetto et al, 2018]. There are also other works on different directions such linear MDP with a generative model [Lu et al, 2021], non-stationary sequential learning [Qin et al, 2022], and linear dynamical systems [Modi et al, 2021].…”
Section: Related Workmentioning
confidence: 99%
“…since η t is an independent random variable with zero mean. It can be derived (more details can be found in the extended version of this paper [29]) that E s 1 2 ≤ 2cφ 2 max ε 2 for some constant c and E s…”
Section: B Representation Learning In Sequential Tasksmentioning
confidence: 99%
“…Proof of Theorem 3.5: After the RE phase of nth cycle in the SeqRepL algorithm, it can be derived (more details can be found in the extended version of this paper [29]) that the estimate B and the true representation…”
Section: B Representation Learning In Sequential Tasksmentioning
confidence: 99%