{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T17:04:58Z","timestamp":1781370298335,"version":"3.54.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832001"],"award-info":[{"award-number":["61832001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tnnls.2021.3128666","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T20:31:14Z","timestamp":1638390674000},"page":"4816-4825","source":"Crossref","is-referenced-by-count":7,"title":["Empowering the Diversity and Individuality of Option: Residual Soft Option Critic Framework"],"prefix":"10.1109","volume":"34","author":[{"given":"Anjie","family":"Zhu","sequence":"first","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0928-6899","authenticated-orcid":false,"given":"Feiyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2081-555X","authenticated-orcid":false,"given":"Hui","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2259-886X","authenticated-orcid":false,"given":"Deqiang","family":"Ouyang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2615-1555","authenticated-orcid":false,"given":"Jie","family":"Shao","sequence":"additional","affiliation":[{"name":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Exploration in reinforcement learning with deep covering options","author":"jinnai","year":"2020","journal-title":"Proc 8th Int Conf Learn Represent (ICLR)"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref12","first-page":"3130","article-title":"Discovering options for exploration by minimizing cover time","author":"jinnai","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref34","first-page":"1","article-title":"Learnings options end-to-end for continuous action tasks","author":"klissarov","year":"2017","journal-title":"Proc NIPS Hierarchical Reinforcement Learn Workshop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066385"},{"key":"ref37","article-title":"SOAC: The soft option actor-critic architecture","author":"li","year":"2020","journal-title":"arXiv 2006 14363"},{"key":"ref14","first-page":"127","article-title":"Scaling up approximate value iteration with options: Better policies with fewer iterations","author":"mann","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref36","first-page":"10445","article-title":"Learning abstract options","author":"riemer","year":"2018","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/461"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.66"},{"key":"ref11","first-page":"6401","article-title":"Composing value functions in reinforcement learning","author":"van niekerk","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015789"},{"key":"ref10","first-page":"13031","article-title":"The option keyboard: Combining skills in reinforcement learning","author":"barreto","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","article-title":"Learning to run with actor-critic ensemble","author":"huang","year":"2017","journal-title":"arXiv 1712 08987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039328"},{"key":"ref17","first-page":"1","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref39","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref16","first-page":"4682","article-title":"Learning portable representations for high-level planning","author":"james","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn (ICML)"},{"key":"ref38","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref19","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent (ICLR)"},{"key":"ref18","first-page":"1846","article-title":"Latent space policies for hierarchical reinforcement learning","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref24","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"576","article-title":"Exploration-exploitation in MDPs with options","author":"fruit","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref26","first-page":"1611","article-title":"Deep residual reinforcement learning","author":"zhang","year":"2020","journal-title":"Proc 19th Int Conf Auto Agents Multiagent Syst (AAMAS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref20","first-page":"1","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref42","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019876"},{"key":"ref22","first-page":"316","article-title":"PAC-inspired option discovery in lifelong reinforcement learning","author":"brunskill","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref21","first-page":"1","article-title":"Hierarchical reinforcement learning via advantage-weighted information maximization","author":"osa","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent (ICLR)"},{"key":"ref43","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref28","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref27","first-page":"4148","article-title":"The arcade learning environment: An evaluation platform for general agents (extended abstract)","author":"bellemare","year":"2015","journal-title":"Proc 24th Joint Conf Artif Intell (IJCAI)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2018.1509018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891792"},{"key":"ref9","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref3","first-page":"39:1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref40","first-page":"1579","article-title":"Convergent combinations of reinforcement learning with linear function approximation","author":"schoknecht","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10208115\/09632279.pdf?arnumber=9632279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:01:04Z","timestamp":1692640864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":44,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3128666","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}