{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:55:42Z","timestamp":1773248142541,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,19]]},"DOI":"10.1109\/netsoft57336.2023.10175507","type":"proceedings-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T17:18:58Z","timestamp":1689268738000},"page":"152-160","source":"Crossref","is-referenced-by-count":3,"title":["Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity"],"prefix":"10.1109","author":[{"given":"Kaushik","family":"Dey","sequence":"first","affiliation":[{"name":"Ericsson Research (Artificial Intelligence),India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satheesh K.","family":"Perepu","sequence":"additional","affiliation":[{"name":"Ericsson Research (Artificial Intelligence),India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pallab","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Kharagpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abir","family":"Das","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Kharagpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Bounding performance loss in approximate mdp homomorphisms","volume":"21","author":"taylor","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref15","first-page":"4199","article-title":"Mdp homomorphic networks: Group symmetries in reinforcement learning","volume":"33","author":"der pol","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref20","article-title":"Learning cross-domain correspondence for control with dynamics cycle-consistency","author":"zhang","year":"2020","journal-title":"2012 arXiv preprint arXiv"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101770"},{"key":"ref10","article-title":"Approximate homomor-phisms: A framework for non-exact minimization in markov decision processes","author":"ravindran","year":"2004","journal-title":"International conference on knowledge based computer systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2921208"},{"key":"ref2","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"arXiv preprint arXiv 1703 02854"},{"key":"ref1","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2020.07.001"},{"key":"ref16","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"arXiv preprint arXiv 1611 05763"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2100338"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2100338"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001426"},{"key":"ref7","article-title":"Return-based contrastive representation learning for reinforcement learning","author":"liu","year":"2021","journal-title":"arXiv preprint arXiv 2102 10496"},{"key":"ref9","first-page":"11157","article-title":"R1-cyclegan: Reinforcement learning aware simulationto-real","author":"rao","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref3","first-page":"1989","article-title":"Cycada: Cycle-consistent adversarial domain adaptation","author":"hoffman","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS47738.2020.9110408"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"}],"event":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","location":"Madrid, Spain","start":{"date-parts":[[2023,6,19]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 IEEE 9th International Conference on Network Softwarization (NetSoft)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10175164\/10175395\/10175507.pdf?arnumber=10175507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T17:58:27Z","timestamp":1690912707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10175507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/netsoft57336.2023.10175507","relation":{},"subject":[],"published":{"date-parts":[[2023,6,19]]}}}