{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:53:37Z","timestamp":1757703217553,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811572","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"1954-1960","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Policy Learning for Mechanical Search"],"prefix":"10.1109","author":[{"given":"Oussama","family":"Zenkri","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence (BCAI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460887"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560406"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341545"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062295"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197101"},{"key":"ref16","article-title":"Decision making in joint push-grasp action space for large-scale object sorting","author":"pan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967899"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793744"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"journal-title":"Siamese Neural Networks for One-Shot Image Recognition","year":"2015","author":"koch","key":"ref5"},{"key":"ref8","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Tractable planning under uncertainty Exploiting structure","year":"2004","author":"pineau","key":"ref7"},{"key":"ref2","article-title":"How can robots succeed in unstructured environments","author":"katz","year":"0","journal-title":"Workshop on Robot Manipulation Intelligence in Human Environments at Robotics Science and Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759839"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794143"},{"key":"ref20","article-title":"A hybrid approach for learning to shift and grasp with elaborate motion primitives","volume":"abs 2111 1510","author":"feldman","year":"2021","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.24.2.348"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9687"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref23","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80 pmlr","author":"haarnoja","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018 Stockholmsmässan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"journal-title":"pybullet a python module for physics simulation in robotics games and machine learning","year":"2017","author":"coumans","key":"ref25"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811572.pdf?arnumber=9811572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:03:47Z","timestamp":1667516627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811572","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}