DSpace Repository

Policy reuse for dialog management using action-relation probability

Show simple item record

dc.contributor.author Nguyen, Tung. T.
dc.contributor.author Yoshino, Koichiro
dc.contributor.author Sakti, Sakriani
dc.contributor.author Nakamura, Satoshi
dc.date.accessioned 2020-09-18T09:10:19Z
dc.date.available 2020-09-18T09:10:19Z
dc.date.issued 2020-08-19
dc.identifier.uri http://hdl.handle.net/10061/14054
dc.description.abstract We study the problem of policy adaptation for reinforcement-learning-based dialog management. Policy adaptation is a commonly used technique to alleviate the problem of data sparsity when training a goal-oriented dialog system for a new task (the target task) by using knowledge when learning policies in an existing task. The methods used by current works in dialog policy adaptation need much time and effort for adapting because they use reinforcement learning algorithms to train a new policy for the target task from scratch. In this paper, we show that a dialog policy can be learned without training by reinforcement learning in the target task. In contrast to existing works, our proposed method learns the relation in the form of probability distribution between the action sets of the source and the target tasks. Thus, we can immediately derive a policy for the target task, which significantly reduces the adaptation time. Our experiments show that the proposed method learns a new policy for the target task much more quickly. In addition, the learned policy achieves higher performance than policies created by fine-tuning when the amount of available data on the target task is limited. ja_JP
dc.language.iso en ja_JP
dc.publisher IEEE ja_JP
dc.relation.isreplacedby https://ieeexplore.ieee.org/document/9171319 ja_JP
dc.rights This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. ja_JP
dc.title Policy reuse for dialog management using action-relation probability ja_JP
dc.type.nii Journal Article ja_JP
dc.contributor.transcription ヨシノ, コウイチロウ
dc.contributor.transcription ナカムラ, サトシ
dc.contributor.alternative 吉野 , 幸一郎
dc.contributor.alternative 中村, 哲
dc.textversion none ja_JP
dc.identifier.eissn 2169-3536
dc.identifier.jtitle IEEE Access ja_JP
dc.identifier.volume 4 ja_JP
dc.relation.doi 10.1109/ACCESS.2020.3017780 ja_JP
dc.identifier.NAIST-ID 84369867 ja_JP
dc.identifier.NAIST-ID 74651712 ja_JP
dc.identifier.NAIST-ID 73297715 ja_JP
dc.identifier.NAIST-ID 73296626 ja_JP


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account