{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:32:11Z","timestamp":1730255531040,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161058","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"11531-11537","source":"Crossref","is-referenced-by-count":2,"title":["Guiding Reinforcement Learning with Shared Control Templates"],"prefix":"10.1109","author":[{"given":"Abhishek","family":"Padalkar","sequence":"first","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC),Weßling,Germany,82234"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriel","family":"Quere","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC),Weßling,Germany,82234"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franz","family":"Steinmetz","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC),Weßling,Germany,82234"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonin","family":"Raffin","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC),Weßling,Germany,82234"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Nieuwenhuisen","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE,Wachtberg,53343"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o","family":"Silv\u00e9rio","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC),Weßling,Germany,82234"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Freek","family":"Stulp","sequence":"additional","affiliation":[{"name":"German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC),Weßling,Germany,82234"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","volume":"abs 2006 14171","author":"huang","year":"2020","journal-title":"A closer look at invalid action masking in policy gradient algorithms"},{"key":"ref12","volume":"abs 2004 980","author":"kanervisto","year":"2020","journal-title":"Action space shaping in deep reinforcement learning"},{"journal-title":"Learning to close the gap Combining task frame formalism and reinforce-ment learning for compliant vegetable cutting","year":"2020","author":"padalkar","key":"ref15"},{"key":"ref14","first-page":"1357","article-title":"Robot reinforcement learning on the constraint manifold","author":"liu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref11","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","author":"taylor","year":"2020","journal-title":"Learning for Dy-namics and Control"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1981.4308708"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92442-3_11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/70.508440"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2283410"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341156"},{"journal-title":"Stable-baselines3 Reliable reinforcement learning implementations","year":"2021","author":"raffin","key":"ref26"},{"key":"ref25","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref20","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"0","journal-title":"In Proceedings of the Sixteenth International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126658"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197041"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561677"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.027"},{"key":"ref3","article-title":"High acceleration reinforcement learning for real-world juggling with binary rewards","author":"ploeger","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161058.pdf?arnumber=10161058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:37:39Z","timestamp":1690220259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161058","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}