{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:22:14Z","timestamp":1761582134481,"version":"3.40.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"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":[[2021,7,21]]},"DOI":"10.1109\/indin45523.2021.9557406","type":"proceedings-article","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T21:23:04Z","timestamp":1633987384000},"page":"1-7","source":"Crossref","is-referenced-by-count":5,"title":["Hierarchical Reinforcement Learning for Waypoint-based Exploration in Robotic Devices"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Zinn","sequence":"first","affiliation":[{"name":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany"}]},{"given":"Birgit","family":"Vogel-Heuser","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany"}]},{"given":"Fabian","family":"Schuhmann","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany"}]},{"given":"Luis Alberto","family":"Cruz Salazar","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany"}]}],"member":"263","reference":[{"article-title":"Learning multi-level hierarchies with hindsight","year":"2017","author":"levy","key":"ref10"},{"key":"ref11","first-page":"603","article-title":"Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators","author":"li","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"haarnoja","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2003.11.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref17","first-page":"6061","article-title":"Efficient exploration in constrained environments with goal-oriented reference path","author":"ota","year":"2020","journal-title":"IEEE International Conference on Intelligent Robots and Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN.2017.8104776"},{"article-title":"Distributed prioritized experience replay","year":"2018","author":"horgan","key":"ref28"},{"key":"ref4","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1115\/1.4050624"},{"journal-title":"Manipulating industrial robots – Vocabulary (ISO\/DIS 8373 2010)","year":"2010","key":"ref5"},{"article-title":"Feudal networks for hierarchical reinforcement learning","year":"2017","author":"vezhnevets","key":"ref8"},{"key":"ref7","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref9","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914088"},{"article-title":"Go-explore: a new approach for hard-exploration problems","year":"2019","author":"ecoffet","key":"ref22"},{"key":"ref21","first-page":"77","article-title":"Reinforcement learning of material flow control logic using hardware-in-the-loop simulation","author":"jaensch","year":"2019","journal-title":"First International Conference on Artificial Intelligence for Industries (AI4I)"},{"key":"ref24","article-title":"Researching evolution in industrial plant automation: Scenarios and documentation of the pick and place unit","author":"vogel-heuser","year":"2014","journal-title":"Tech Rep"},{"article-title":"The problem with ddpg: understanding failures in deterministic environments with sparse rewards","year":"2019","author":"matheron","key":"ref23"},{"article-title":"Dueling network architectures for deep reinforcement learning","year":"2015","author":"wang","key":"ref26"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"}],"event":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","start":{"date-parts":[[2021,7,21]]},"location":"Palma de Mallorca, Spain","end":{"date-parts":[[2021,7,23]]}},"container-title":["2021 IEEE 19th International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9557349\/9557353\/09557406.pdf?arnumber=9557406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T18:29:15Z","timestamp":1744050555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9557406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/indin45523.2021.9557406","relation":{},"subject":[],"published":{"date-parts":[[2021,7,21]]}}}