{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:49:42Z","timestamp":1777567782031,"version":"3.51.4"},"reference-count":33,"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"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry & Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008122","name":"Institute of Information & communications Technology Planning & Evaluation (IITP)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008122","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160371","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"1673-1679","source":"Crossref","is-referenced-by-count":16,"title":["Adaptive and Explainable Deployment of Navigation Skills via Hierarchical Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kyowoon","family":"Lee","sequence":"first","affiliation":[{"name":"Ulsan National Institute of Science and Technology,Department of Computer Science and Engineering,Ulsan,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seongun","family":"Kim","sequence":"additional","affiliation":[{"name":"Graduate School of Artificial Intelligence, Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea,34141"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaesik","family":"Choi","sequence":"additional","affiliation":[{"name":"Graduate School of Artificial Intelligence, Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea,34141"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"25 146","article-title":"Learning to synthesize programs as interpretable and generalizable policies","volume":"34","author":"trivedi","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v14i1.13033"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636594"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref30","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560951"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197148"},{"key":"ref32","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":"Int Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/machines6030033"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.940150"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341783"},{"key":"ref16","article-title":"Fully distributed multi-robot collision avoidance via deep reinforcement learning for safe and efficient navigation in complex scenarios","author":"fan","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref24","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume":"32","author":"trott","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0467-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref20","article-title":"Hind-sight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref21","article-title":"Dher: Hindsight experience replay for dynamic goals","author":"fang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811797"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2007.4282736"},{"key":"ref29","first-page":"495","author":"hengst","year":"2010","journal-title":"Hierarchical Reinforcement Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2996593"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891491"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2017.8244199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341540"},{"key":"ref5","first-page":"2255","article-title":"Social gan: Socially acceptable trajectories with generative adversarial net-works","author":"gupta","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"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\/10160371.pdf?arnumber=10160371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:29:55Z","timestamp":1690219795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160371","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}