{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:23:35Z","timestamp":1740108215396,"version":"3.37.3"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science for Technological Innovation"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s00138-023-01492-1","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T13:02:28Z","timestamp":1701349348000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to explore by reinforcement over high-level options"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5921-1505","authenticated-orcid":false,"given":"Juncheng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brendan","family":"McCane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Mills","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"1492_CR1","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"1492_CR2","doi-asserted-by":"crossref","unstructured":"Chang, A., Dai, A., Funkhouser, T., et\u00a0al.: Matterport3d: learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"1492_CR3","unstructured":"Chaplot, D.S., Gandhi, D., Gupta, S., et\u00a0al.: Learning to explore using active neural slam. arXiv preprint arXiv:2004.05155 (2020)"},{"key":"1492_CR4","unstructured":"Chen, T., Gupta, S., Gupta, A.: Learning exploration policies for navigation. arXiv preprint arXiv:1903.01959 (2019)"},{"key":"1492_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1492_CR6","doi-asserted-by":"crossref","unstructured":"Henriques, J.F., Vedaldi, A.: Mapnet: an allocentric spatial memory for mapping environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8476\u20138484 (2018)","DOI":"10.1109\/CVPR.2018.00884"},{"key":"1492_CR7","doi-asserted-by":"crossref","unstructured":"Klein, G., Murray, D.: Parallel tracking and mapping for small ar workspaces. In: 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. IEEE, pp. 225\u2013234 (2007)","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"1492_CR8","unstructured":"Mnih, V., Badia, A.P., Mirza, M., et\u00a0al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, PMLR, pp. 1928\u20131937 (2016)"},{"issue":"5","key":"1492_CR9","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"1492_CR10","unstructured":"Paszke, A., Gross, S., Massa, F., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., et\u00a0al (eds) Advances in Neural Information Processing Systems 32. Curran Associates, Inc., pp. 8024\u20138035, http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf (2019)"},{"key":"1492_CR11","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., et\u00a0al.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, PMLR, pp. 2778\u20132787 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"1492_CR12","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Al-Halah, Z., Grauman, K.: Occupancy anticipation for efficient exploration and navigation. In: European Conference on Computer Vision. Springer, pp. 400\u2013418 (2020)","DOI":"10.1007\/978-3-030-58558-7_24"},{"issue":"5","key":"1492_CR13","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1007\/s11263-021-01437-z","volume":"129","author":"SK Ramakrishnan","year":"2021","unstructured":"Ramakrishnan, S.K., Jayaraman, D., Grauman, K.: An exploration of embodied visual exploration. Int. J. Comput. Vis. 129(5), 1616\u20131649 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"1492_CR14","doi-asserted-by":"crossref","unstructured":"Savva, M., Kadian, A., Maksymets, O., et\u00a0al.: Habitat: A platform for embodied AI research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9339\u20139347 (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"1492_CR15","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., et\u00a0al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"4","key":"1492_CR16","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1073\/pnas.93.4.1591","volume":"93","author":"JA Sethian","year":"1996","unstructured":"Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. Proc. Natl. Acad. Sci. 93(4), 1591\u20131595 (1996)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"1\u20132","key":"1492_CR17","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"1492_CR18","unstructured":"Tang, H., Houthooft, R., Foote, D., et\u00a0al.: # exploration: a study of count-based exploration for deep reinforcement learning. In: 31st Conference on Neural Information Processing Systems (NIPS), pp. 1\u201318 (2017)"},{"issue":"1","key":"1492_CR19","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/BF02204836","volume":"32","author":"CC White","year":"1991","unstructured":"White, C.C.: A survey of solution techniques for the partially observed Markov decision process. Ann. Oper. Res. 32(1), 215\u2013230 (1991)","journal-title":"Ann. Oper. Res."},{"key":"1492_CR20","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z., et\u00a0al.: Gibson env: real-world perception for embodied agents. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9068\u20139079 (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"1492_CR21","unstructured":"Yamauchi, B.: A frontier-based approach for autonomous exploration. In: Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA\u201997.\u2019Towards New Computational Principles for Robotics and Automation\u2019. IEEE, pp. 146\u2013151 (1997)"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01492-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01492-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01492-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T09:06:04Z","timestamp":1706000764000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01492-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":21,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["1492"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01492-1","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"26 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"6"}}