{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:03:41Z","timestamp":1755795821469,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"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":["11801563"],"award-info":[{"award-number":["11801563"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,6]]},"DOI":"10.1109\/dsaa53316.2021.9564185","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T22:54:28Z","timestamp":1634770468000},"page":"1-12","source":"Crossref","is-referenced-by-count":6,"title":["Feature-Option-Action: A domain adaption transfer reinforcement learning framework"],"prefix":"10.1109","author":[{"given":"Yunxiao","family":"Zhang","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Center, DII,Beijing,China"}]},{"given":"Xiaochuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, DII,Beijing,China"}]},{"given":"Tianlong","family":"Shen","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, DII,Beijing,China"}]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, DII,Beijing,China"}]},{"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, DII,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13560-1_76"},{"key":"ref13","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"tzeng","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"The option-critic architecture","volume":"31","author":"bacon","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MFI.2001.1013500"},{"key":"ref17","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992700"},{"journal-title":"Temporal Abstraction in Reinforcement Learning","year":"2000","author":"precup","key":"ref19"},{"key":"ref28","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.61"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143906"},{"key":"ref6","article-title":"Model-based reinforcement learning: A survey","author":"moerland","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Attend, adapt and transfer: Attentive deep architecture for adaptive transfer from multiple sources in the same domain","author":"rajendran","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"506","article-title":"Cross-domain knowledge transfer using structured representations","volume":"6","author":"swarup","year":"2006","journal-title":"AAAI"},{"key":"ref7","first-page":"2169","article-title":"Learning modular neural network policies for multitask and multi-robot transfer","author":"devin","year":"0","journal-title":"2017 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462977"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273607"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"ref21","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Portable option discovery for automated learning transfer in object-oriented markov decision processes","author":"topin","year":"0","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"ref23","first-page":"895","article-title":"Building portable options: Skill transfer in reinforcement learning","volume":"7","author":"konidaris","year":"2007","journal-title":"IJCAI"},{"key":"ref26","first-page":"608","article-title":"Relativized options: Choosing the right transformation","author":"ravindran","year":"0","journal-title":"Proceedings of the 20th International Conference on Machine Learning (ICML-03)"},{"key":"ref25","first-page":"2054","article-title":"Effective control knowledge transfer through learning skill and representation hierarchies","volume":"7","author":"asadi","year":"2007","journal-title":"IJCAI"}],"event":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","start":{"date-parts":[[2021,10,6]]},"location":"Porto, Portugal","end":{"date-parts":[[2021,10,9]]}},"container-title":["2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564091\/9564109\/09564185.pdf?arnumber=9564185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:37:37Z","timestamp":1659483457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/dsaa53316.2021.9564185","relation":{},"subject":[],"published":{"date-parts":[[2021,10,6]]}}}