Non-Stationary Representation Learning in Sequential Linear Bandits
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 different environments. The embeddings of tasks in each environment share a low...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Open Journal of Control Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9783063/ |
| _version_ | 1797797558982017024 |
|---|---|
| author | Yuzhen Qin Tommaso Menara Samet Oymak ShiNung Ching Fabio Pasqualetti |
| author_facet | Yuzhen Qin Tommaso Menara Samet Oymak ShiNung Ching Fabio Pasqualetti |
| author_sort | Yuzhen Qin |
| collection | DOAJ |
| description | 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 different environments. The embeddings of tasks in each environment share a low-dimensional feature extractor called <italic>representation</italic>, and representations are different across environments. We propose an online algorithm that facilitates efficient decision-making by learning and transferring non-stationary representations in an adaptive fashion. We prove that our algorithm significantly outperforms the existing ones that treat tasks independently. We also conduct experiments using both synthetic and real data to validate our theoretical insights and demonstrate the efficacy of our algorithm. |
| first_indexed | 2024-03-13T03:50:10Z |
| format | Article |
| id | doaj.art-c2b8573a14a94f4ebddc2b0428ee55af |
| institution | Directory Open Access Journal |
| issn | 2694-085X |
| language | English |
| last_indexed | 2024-03-13T03:50:10Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Control Systems |
| spelling | doaj.art-c2b8573a14a94f4ebddc2b0428ee55af2023-06-22T16:06:33ZengIEEEIEEE Open Journal of Control Systems2694-085X2022-01-011415610.1109/OJCSYS.2022.31785409783063Non-Stationary Representation Learning in Sequential Linear BanditsYuzhen Qin0https://orcid.org/0000-0003-1851-1370Tommaso Menara1https://orcid.org/0000-0002-5523-2170Samet Oymak2https://orcid.org/0000-0001-5203-0752ShiNung Ching3https://orcid.org/0000-0003-4063-7068Fabio Pasqualetti4https://orcid.org/0000-0002-8457-8656Department of Mechanical Engineering, University of California, Riverside, CA, USADepartment of Mechanical and Aerospace Engineering, University of California, San Diego, La Jolla CA, USADepartment of Electrical and Computer Engineering, University of California, Riverside, CA, USADepartment of Electrical and Systems Engineering and Biomedical Engineering, Washington University in St. Louis, St. Louis, MO, USADepartment of Mechanical Engineering, University of California, Riverside, CA, USAIn 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 different environments. The embeddings of tasks in each environment share a low-dimensional feature extractor called <italic>representation</italic>, and representations are different across environments. We propose an online algorithm that facilitates efficient decision-making by learning and transferring non-stationary representations in an adaptive fashion. We prove that our algorithm significantly outperforms the existing ones that treat tasks independently. We also conduct experiments using both synthetic and real data to validate our theoretical insights and demonstrate the efficacy of our algorithm.https://ieeexplore.ieee.org/document/9783063/Linear banditsnon-stationary representationsrepresentation learning |
| spellingShingle | Yuzhen Qin Tommaso Menara Samet Oymak ShiNung Ching Fabio Pasqualetti Non-Stationary Representation Learning in Sequential Linear Bandits IEEE Open Journal of Control Systems Linear bandits non-stationary representations representation learning |
| title | Non-Stationary Representation Learning in Sequential Linear Bandits |
| title_full | Non-Stationary Representation Learning in Sequential Linear Bandits |
| title_fullStr | Non-Stationary Representation Learning in Sequential Linear Bandits |
| title_full_unstemmed | Non-Stationary Representation Learning in Sequential Linear Bandits |
| title_short | Non-Stationary Representation Learning in Sequential Linear Bandits |
| title_sort | non stationary representation learning in sequential linear bandits |
| topic | Linear bandits non-stationary representations representation learning |
| url | https://ieeexplore.ieee.org/document/9783063/ |
| work_keys_str_mv | AT yuzhenqin nonstationaryrepresentationlearninginsequentiallinearbandits AT tommasomenara nonstationaryrepresentationlearninginsequentiallinearbandits AT sametoymak nonstationaryrepresentationlearninginsequentiallinearbandits AT shinungching nonstationaryrepresentationlearninginsequentiallinearbandits AT fabiopasqualetti nonstationaryrepresentationlearninginsequentiallinearbandits |