Reinforcement learning with attention that works: a self-supervised approach

Date

2019

Authors

Manchin, A.
Abbasnejad, E.
Van Den Hengel, A.

Editors

Gedeon, T.
Wong, K.W.
Lee, M.

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Communications in Computer and Information Science, 2019 / Gedeon, T., Wong, K.W., Lee, M. (ed./s), vol.1143 CCIS, pp.223-230

Statement of Responsibility

Anthony Manchin, Ehsan Abbasnejad, and Anton van den Hengel

Conference Name

International Conference on Neural Information Processing (ICONIP) (12 Dec 2019 - 15 Dec 2019 : Sydney, Australia)

Abstract

Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. Unlike the selective attention models used in previous attempts, which constrain the attention via preconceived notions of importance, our implementation utilises the Markovian properties inherent in the state input. We propose the first combination of self attention and reinforcement learning that is capable of producing significant improvements, including new state of the art results in the Arcade Learning Environment.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© Springer Nature Switzerland AG 2019

License

Grant ID

Call number

Persistent link to this record