WEKO3
アイテム
Sigmoid-weighted linear units for neural network function approximation in reinforcement learning
https://oist.repo.nii.ac.jp/records/659
https://oist.repo.nii.ac.jp/records/659df473d29-d03c-4035-8804-88112a5c1119
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
1-s2.0-S0893608017302976-main (1.4 MB)
|
Creative Commons Attribution-NonCommercial-NoDerivatives License
(http://creativecommons.org/Licenses/by-nc-nd/4.0/) |
| Item type | 学術雑誌論文 / Journal Article(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2018-08-14 | |||||||||||
| タイトル | ||||||||||||
| タイトル | Sigmoid-weighted linear units for neural network function approximation in reinforcement learning | |||||||||||
| 言語 | en | |||||||||||
| 言語 | ||||||||||||
| 言語 | eng | |||||||||||
| 資源タイプ | ||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||
| 資源タイプ | journal article | |||||||||||
| 著者（英） |
Elfwing, Stefan
× Elfwing, Stefan
× Uchibe, Eiji
× Doya, Kenji
|
|||||||||||
| 書誌情報 |
en : Neural Networks 発行日 2018-01-11 |
|||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). The activation of the SiLU is computed by the sigmoid function multiplied by its input. Second, we suggest that the more traditional approach of using on-policy learning with eligibility traces, instead of experience replay, and softmax action selection can be competitive with DQN, without the need for a separate target network. We validate our proposed approach by, first, achieving new state-of-the-art results in both stochastic SZ-Tetris and Tetris with a small 10 x 10 board, using TD(lambda) learning and shallow dSiLU network agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa(lambda) agent with SiLU and dSiLU hidden units. | |||||||||||
| 出版者 | ||||||||||||
| 出版者 | Elsevier Ltd. | |||||||||||
| ISSN | ||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||
| 収録物識別子 | 0893-6080 | |||||||||||
| PubMed番号 | ||||||||||||
| 関連タイプ | isIdenticalTo | |||||||||||
| 識別子タイプ | PMID | |||||||||||
| 関連識別子 | info:pmid/29395652 | |||||||||||
| DOI | ||||||||||||
| 関連タイプ | isIdenticalTo | |||||||||||
| 識別子タイプ | DOI | |||||||||||
| 関連識別子 | info:doi/10.1016/j.neunet.2017.12.012 | |||||||||||
| 権利 | ||||||||||||
| 権利情報 | © 2017 The Author(s). | |||||||||||
| 関連サイト | ||||||||||||
| 識別子タイプ | URI | |||||||||||
| 関連識別子 | https://www.sciencedirect.com/science/article/pii/S0893608017302976 | |||||||||||
| 著者版フラグ | ||||||||||||
| 出版タイプ | VoR | |||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||
