{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:30Z","timestamp":1740165810924,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology Council (NSTC), Taiwan","award":["MOST 111-2223-E-007-004-MY3","MOST 111-2628-E-007-010"],"award-info":[{"award-number":["MOST 111-2223-E-007-004-MY3","MOST 111-2628-E-007-010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tnnls.2022.3213606","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:34:41Z","timestamp":1667525681000},"page":"7251-7258","source":"Crossref","is-referenced-by-count":1,"title":["Composing Synergistic Macro Actions for Reinforcement Learning Agents"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0969-6270","authenticated-orcid":false,"given":"Yu-Ming","family":"Chen","sequence":"first","affiliation":[{"name":"Taiwan Semiconductor Manufacturing Company (TSMC), Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1120-2970","authenticated-orcid":false,"given":"Kaun-Yu","family":"Chang","sequence":"additional","affiliation":[{"name":"Avery Design Systems Inc., Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chien","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Electrical Engineering, University of Rostock, Rostock, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsu-Ching","family":"Hsiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang-Wei","family":"Hong","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4680-4800","authenticated-orcid":false,"given":"Chun-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Roles of macro-actions in accelerating reinforcement learning","volume-title":"Proc. Grace Hopper Celebration Women Comput.","volume":"1317","author":"McGovern"},{"key":"ref2","first-page":"15","volume-title":"Macro-actions in reinforcement learning: An empirical analysis","author":"McGovern","year":"1998"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.5230"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2009.5346139"},{"key":"ref5","first-page":"1","article-title":"Frame skip is a powerful parameter for learning to play Atari","volume-title":"Proc. Assoc. Advancement Artif. Intell. (AAAI) Conf. Workshop","author":"Braylan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2006.385067"},{"key":"ref7","first-page":"256","article-title":"Learning macro-actions for arbitrary planners and domains","volume-title":"Proc. Int. Conf. Automated Planning Scheduling (ICAPS)","author":"Newton"},{"key":"ref8","article-title":"Deep reinforcement learning with macro-actions","volume-title":"arXiv:1606.04615","author":"Durugkar","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIBD.2018.8396173"},{"key":"ref10","first-page":"1","article-title":"Designing neural network architectures using reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Baker"},{"key":"ref11","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zoph"},{"key":"ref12","article-title":"DARTS: Differentiable architecture search","volume-title":"arXiv:1806.09055","author":"Liu","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"volume-title":"Stable Baselines","year":"2018","author":"Hill","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref20","first-page":"1","article-title":"Learning to repeat: Fine grained action repetition for deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Sharma"},{"key":"ref21","first-page":"3486","article-title":"Strategic attentive writer for learning macro-actions","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Vezhnevets"},{"key":"ref22","first-page":"118","article-title":"Using loops in decision-theoretic refinement planners","volume-title":"Proc. AIPS","author":"Goodwin"},{"key":"ref23","first-page":"1045","article-title":"Learning macro-actions in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Randlov"},{"key":"ref24","article-title":"Macro action reinforcement learning with sequence disentanglement using variational autoencoder","volume-title":"arXiv:1903.09366","author":"Kim","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1696"},{"key":"ref26","first-page":"163","article-title":"Genetically evolved macro-actions in AI planning problems","volume-title":"Proc. 24th UK Planning Scheduling SIG","author":"Newton"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2077"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2013.123"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(85)90012-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v25i1.13703"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017546"},{"key":"ref32","first-page":"231","article-title":"Learning partial-order macros from solutions","volume-title":"Proc. ICAPS","author":"Botea"},{"key":"ref33","first-page":"1828","article-title":"Fast planning with iterative macros","volume-title":"Proc. IJCAI","author":"Botea"},{"key":"ref34","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bellemare"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10517792\/09934932.pdf?arnumber=9934932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:52:25Z","timestamp":1714762345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9934932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":34,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3213606","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}