{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:14:06Z","timestamp":1730229246186,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"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":[[2024,2,22]]},"DOI":"10.1109\/icara60736.2024.10553128","type":"proceedings-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T17:29:21Z","timestamp":1718731761000},"page":"328-333","source":"Crossref","is-referenced-by-count":0,"title":["Learning and Reusing Primitive Behaviours to Improve Hindsight Experience Replay Sample Efficiency"],"prefix":"10.1109","author":[{"given":"Francisco Roldan","family":"Sanchez","sequence":"first","affiliation":[{"name":"Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland"}]},{"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"University College Dublin,Dublin,Ireland"}]},{"given":"David Cordova","family":"Bulens","sequence":"additional","affiliation":[{"name":"University College Dublin,Dublin,Ireland"}]},{"given":"Kevin","family":"McGuinness","sequence":"additional","affiliation":[{"name":"Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland"}]},{"given":"Stephen J.","family":"Redmond","sequence":"additional","affiliation":[{"name":"University College Dublin,Insight SFI Centre for Data Analytics,Dublin,Ireland"}]},{"given":"Noel E.","family":"O'Connor","sequence":"additional","affiliation":[{"name":"Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18178\/ijmerr.10.10.526-535"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18178\/ijmerr.9.8.1134-1139"},{"journal-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"Matthias","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.538773"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICARA56516.2023.10125281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"journal-title":"Pri-oritized experience replay","year":"2015","author":"Tom","key":"ref8"},{"journal-title":"Experi-ence replay optimization","year":"2019","author":"Daochen","key":"ref9"},{"key":"ref10","article-title":"Hindsight experience replay","volume":"30","author":"Marcin","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF01442176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref14","article-title":"Ex-ploration via hindsight goal generation","volume":"32","author":"Zhizhou","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref17","first-page":"6131","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Kimin","year":"2021"},{"key":"ref18","first-page":"11501","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume":"34","author":"Tianhe","year":"2021","journal-title":"Advances in Neural Information Pro-cessing Systems"},{"key":"ref19","article-title":"Behavioral cloning from noisy demonstrations","volume-title":"International Conference on Learning Representations","author":"Fumihiro","year":"2020"},{"journal-title":"Efficient Multi-Task Reinforcement Learning via Selective Behavior Sharing","year":"2023","author":"Grace","key":"ref20"},{"key":"ref21","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Lili","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Michael","year":"2021","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2024 10th International Conference on Automation, Robotics and Applications (ICARA)","start":{"date-parts":[[2024,2,22]]},"location":"Athens, Greece","end":{"date-parts":[[2024,2,24]]}},"container-title":["2024 10th International Conference on Automation, Robotics and Applications (ICARA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10552867\/10552915\/10553128.pdf?arnumber=10553128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:12:41Z","timestamp":1719342761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10553128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icara60736.2024.10553128","relation":{},"subject":[],"published":{"date-parts":[[2024,2,22]]}}}