Advanced search: Search from
Select basic information for advanced search
| Free word |
|---|
| Copy service |  |
|---|---|
| Related links |  |
| Publisher site |  |
Art
J-GLOBAL ID：202202215168992131
Reference number：22A1339930 Relationship between Computational Performance and Task Difficulty of Reinforcement Learning Methods Using Reward Machines
リワードマシンを用いる強化学習手法の計算性能とタスク難易度の関係
ClipsWATANABE RYUJI
About WATANABE RYUJI
(東大 大学院工学系研究科)
, About 東大 大学院工学系研究科
TANAKA GOHEI
About TANAKA GOHEI
(東大 国際高等研 ニューロインテリジェンス国際研究機構)
About 東大 国際高等研 ニューロインテリジェンス国際研究機構
Material：
電子情報通信学会技術研究報告(Web)
(IEICE Technical Report (Web))
About 電子情報通信学会技術研究報告(Web)
Volume： 121 Issue： 444(NLP2021 126-152) Page： 77-82 (WEB ONLY) Publication year： Mar. 21, 2022
JST Material Number： U2030A ISSN： 2432-6380 Document type： Proceedings
Article type： 原著論文 Country of issue： Japan (JPN) Language： JAPANESE (JA)
Thesaurus term：
Semi thesaurus term：
Thesaurus term/Semi thesaurus term
Keywords indexed to the article.
All keywords is available on JDreamIII(charged).
On J-GLOBAL, this item will be available after more than half a year after the record posted. In addtion, medical articles require to login to MyJ-GLOBAL.
Keywords indexed to the article.
All keywords is available on JDreamIII(charged).
On J-GLOBAL, this item will be available after more than half a year after the record posted. In addtion, medical articles require to login to MyJ-GLOBAL.
*reinforcement learning
, About reinforcement learning
*degree
, About degree
function (mathematics)
, About function (mathematics)
non-Markov process
, About non-Markov process
Learning
, About Learning
*performance
, About performance
experiment
, About experiment
symbol
, About symbol
calculation
, About calculation
Learning performance
, About Learning performance
numerical experiment
About numerical experiment
Semi thesaurus term：
Thesaurus term/Semi thesaurus term
Keywords indexed to the article.
All keywords is available on JDreamIII(charged).
On J-GLOBAL, this item will be available after more than half a year after the record posted. In addtion, medical articles require to login to MyJ-GLOBAL.
Keywords indexed to the article.
All keywords is available on JDreamIII(charged).
On J-GLOBAL, this item will be available after more than half a year after the record posted. In addtion, medical articles require to login to MyJ-GLOBAL.
symbol
, About symbol
*degree of difficulty
, About degree of difficulty
reward function
About reward function
JST classification (1)：
JST classification
Category name(code) classified by JST.
Artificial intelligence
Category name(code) classified by JST.
(JE08000Z)
About Artificial intelligence
Reference (17)：
- R.S. Sutton and A.G. Barto, Reinforcement learning: An introduction, MIT press, 2018.
- A. Camacho, O. Chen, S. Sanner, and S.A. McIlraith, “Decision-making with non-markovian rewards: From ltl to automata-based reward shaping,” Proceedings of the Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), pp.279-283, 2017.
- F. Bacchus, C. Boutilier, and A. Grove, “Rewarding behaviors,” Proceedings of the Thirteenth National Conference on Artificial Intelligence - Volume 2, p.1160-1167, AAAI’96, AAAI Press, 1996.
- R. Brafman, G. De Giacomo, and F. Patrizi, “LTLf/LDLf Non-Markovian Rewards,” Proceedings of the AAAI Conference on Artificial Intelligence, vol.32, pp.1771-1778, 2018.
- C.J.C.H. Watkins, “Learning from delayed rewards,” 1989.
Terms in the title (5)：
Terms in the title
Keywords automatically extracted from the title.
Keywords automatically extracted from the title.
強化学習
, About 強化学習
手法
, About 手法
計算
, About 計算
タスク
, About タスク
難易度
About 難易度
Return to Previous Page
