{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:52:01Z","timestamp":1770742321795,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1109\/ro-man53752.2022.9900738","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:57:30Z","timestamp":1664567850000},"page":"1498-1505","source":"Crossref","is-referenced-by-count":5,"title":["A Sample Efficiency Improved Method via Hierarchical Reinforcement Learning Networks"],"prefix":"10.1109","author":[{"given":"Qinghua","family":"Chen","sequence":"first","affiliation":[{"name":"Oakland University,Intelligent Robotics Laboratory,MI,USA,48309"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evan","family":"Dallas","sequence":"additional","affiliation":[{"name":"Oakland University,Intelligent Robotics Laboratory,MI,USA,48309"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pourya","family":"Shahverdi","sequence":"additional","affiliation":[{"name":"Oakland University,Intelligent Robotics Laboratory,MI,USA,48309"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jessica","family":"Korneder","sequence":"additional","affiliation":[{"name":"Oakland University,Applied Behavior Analysis Clinic,MI,USA,48309"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osamah A.","family":"Rawashdeh","sequence":"additional","affiliation":[{"name":"Oakland University,Embedded Systems Research Lab,MI,USA,48309"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wing-Yue","family":"Geoffrey Louie","sequence":"additional","affiliation":[{"name":"Oakland University,Intelligent Robotics Laboratory,MI,USA,48309"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010461"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-88431-0"},{"key":"ref31","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref30","first-page":"233","article-title":"End-to-end incremental learning","author":"castro","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref10","article-title":"Behavior regularized offline reinforcement learning","author":"wu","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.07.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05849-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487168"},{"key":"ref15","article-title":"Residual reinforcement learning from demonstrations","author":"alakuijala","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00818-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"15 923","DOI":"10.1609\/aaai.v35i18.17958","article-title":"Remember more by recalling less: Investigating the role of batch size in continual learning with experience replay (student abstract)","volume":"35","author":"wo?czyk","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref19","first-page":"4063","article-title":"Sparse feature selection makes batch reinforcement learning more sample efficient","author":"hao","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref28","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62056-1_35"},{"key":"ref27","article-title":"Deep reinforcement learning with quantum-inspired experience replay","author":"wei","year":"2021","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref3","first-page":"1224","article-title":"In-the-wild learning from demonstration for therapies for autism spectrum disorder","author":"korneder","year":"2021","journal-title":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref29","first-page":"1125","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref5","article-title":"Improving learning from demonstrations by learning from experience","author":"liu","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/7588221"},{"key":"ref7","first-page":"2469","article-title":"Policy optimization with demonstrations","author":"kang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759144"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794074"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref20","article-title":"Stratified experience replay: Correcting multiplicity bias in off-policy reinforcement learning","author":"daley","year":"2021"},{"key":"ref22","first-page":"3061","article-title":"Revisiting fundamentals of experience replay","author":"fedus","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"A deeper look at experience replay","author":"zhang","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8636075"},{"key":"ref26","article-title":"Forgetful experience replay in hierarchical reinforcement learning from demonstrations","volume":"abs 2006 9939","author":"skrynnik","year":"2020","journal-title":"CoRR"},{"key":"ref25","article-title":"A framework of dual replay buffer: balancing forgetting and generalization in reinforcement learning","author":"zhang","year":"2019","journal-title":"Proceedings of the 2nd Workshop on Scaling Up Reinforcement Learning (SURL) International Joint Conference on Artificial Intelligence (IJCAI)"}],"event":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Napoli, Italy","start":{"date-parts":[[2022,8,29]]},"end":{"date-parts":[[2022,9,2]]}},"container-title":["2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9900506\/9900507\/09900738.pdf?arnumber=9900738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:04:32Z","timestamp":1667516672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9900738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ro-man53752.2022.9900738","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]}}}