{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:40:39Z","timestamp":1730256039530,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611594","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"508-514","source":"Crossref","is-referenced-by-count":0,"title":["Adapting to the \u201cOpen World\u201d: The Utility of Hybrid Hierarchical Reinforcement Learning and Symbolic Planning"],"prefix":"10.1109","author":[{"given":"Pierrick","family":"Lorang","sequence":"first","affiliation":[{"name":"Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA"}]},{"given":"Helmut","family":"Horvath","sequence":"additional","affiliation":[{"name":"TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria"}]},{"given":"Tobias","family":"Kietreiber","sequence":"additional","affiliation":[{"name":"TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria"}]},{"given":"Patrik","family":"Zips","sequence":"additional","affiliation":[{"name":"AIT Austrian Institute of Technology GmbH, Center for Vision, Automation & Control,Vienna,Austria"}]},{"given":"Clemens","family":"Heitzinger","sequence":"additional","affiliation":[{"name":"TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria"}]},{"given":"Matthias","family":"Scheutz","sequence":"additional","affiliation":[{"name":"Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA"}]}],"member":"263","reference":[{"article-title":"A novelty-centric agent architecture for changing worlds","volume-title":"Proceedings of 20th International Conference on Autonomous Agents and Multiagent Systems","author":"Muhammad","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref4","first-page":"52","article-title":"Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges","volume-title":"Information Fusion","volume":"58","author":"Lesort","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"ref6","first-page":"14784","article-title":"You only live once: Single-life reinforcement learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"1","article-title":"Rapid-learn: A framework for learning to recover for handling novelties in open-world environments","volume-title":"IEEE International Conference on Development and Learning (ICDL), London, UK, September 12 - 15, 2022","author":"Goel"},{"key":"ref8","first-page":"1118","article-title":"Spotter: Extending symbolic planning operators through targeted reinforcement learning","volume-title":"Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems","author":"Sarathy"},{"article-title":"Speeding-up continual learning through information gains in novel experiences","volume-title":"4th Planning and Reinforcement Learning (PRL) Workshop at IJCAI2022","author":"Lorang","key":"ref9"},{"key":"ref10","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","author":"Dosovitskiy"},{"year":"2022","key":"ref11","article-title":"Bridging the gap between ai planning and reinforcement learning (prl @ icaps)"},{"year":"2022","key":"ref12","article-title":"Bridging the gap between ai planning and reinforcement learning (prl @ ijcai)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/675"},{"article-title":"Neuro-symbolic world models for adapting to open world novelty","year":"2023","author":"Balloch","key":"ref15"},{"article-title":"Dream architecture: a developmental approach to open-ended learning in robotics","year":"2020","author":"Doncieux","key":"ref16"},{"article-title":"Open-world active learn-\u00b4 ing with stacking ensemble for self-driving cars","year":"2021","author":"Vieira","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"issue":"1","key":"ref19","first-page":"181","article-title":"Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning","volume-title":"Artificial Intelligence","volume":"112","author":"Sutton","year":"1999"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(71)90010-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"issue":"268","key":"ref23","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"Journal of Machine Learning Research","volume":"22","author":"Raffin","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"article-title":"Svqn: Sequential variational soft q-learning networks","volume-title":"International Conference on Learning Representations","author":"Huang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1144"},{"article-title":"PDDL\u2013the Planning Domain Definition Language","year":"1998","author":"McDermott","key":"ref27"},{"article-title":"PDDL\u2013the Planning Domain Definition Language","year":"1998","author":"Ghallab","key":"ref28"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611594.pdf?arnumber=10611594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:19:25Z","timestamp":1723349965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611594","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}