{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:05:44Z","timestamp":1788879944618,"version":"build-2803163510"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"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":[[2024,11,6]]},"DOI":"10.1109\/robot61475.2024.10797413","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:10:37Z","timestamp":1734981037000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Hierarchical Reinforcement Learning and Evolution Strategies for Cooperative Robotic Soccer"],"prefix":"10.1109","author":[{"given":"B\u00e1rbara","family":"Santos","sequence":"first","affiliation":[{"name":"University of Porto,FEUP - Faculty of Engineering,Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ant\u00f3nio","family":"Cardoso","sequence":"additional","affiliation":[{"name":"University of Porto,FEUP - Faculty of Engineering,Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gon\u00e7alo","family":"Le\u00e3o","sequence":"additional","affiliation":[{"name":"University of Porto,FEUP - Faculty of Engineering,Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu\u00eds Paulo","family":"Reis","sequence":"additional","affiliation":[{"name":"University of Porto,FEUP - Faculty of Engineering,Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armando","family":"Sousa","sequence":"additional","affiliation":[{"name":"University of Porto,FEUP - Faculty of Engineering,Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-55015-7_35"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/267658.267738"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref4","volume-title":"Artificial intelligence: a modern approach","author":"Russell","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref6","article-title":"Comparing policy-gradient algorithms","author":"Sutton","year":"2000","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12597-012-0077-2"},{"key":"ref9","article-title":"Reinforcement learning applications","author":"Li","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179075"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.19.7.717"},{"key":"ref13","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107128"},{"key":"ref15","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015059928466"},{"key":"ref17","article-title":"Evolution strategies as a scalable alternative to reinforcement learning. arxiv 2017","author":"Salimans","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref19","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a gpu","author":"Babaeizadeh","year":"2016","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2007.01.003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3189021"},{"key":"ref22","article-title":"Designing a skilled soccer team for robocup: Exploring skill-set-primitives through reinforcement learning","author":"Abreu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 7th Iberian Robotics Conference (ROBOT)","location":"Madrid, Spain","start":{"date-parts":[[2024,11,6]]},"end":{"date-parts":[[2024,11,8]]}},"container-title":["2024 7th Iberian Robotics Conference (ROBOT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10795802\/10796856\/10797413.pdf?arnumber=10797413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:40:12Z","timestamp":1735022412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10797413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/robot61475.2024.10797413","relation":{},"subject":[],"published":{"date-parts":[[2024,11,6]]}}}