{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:52:46Z","timestamp":1742932366042,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031806063"},{"type":"electronic","value":"9783031806070"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-80607-0_18","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T16:35:45Z","timestamp":1735662945000},"page":"228-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Combined Text-Visual Attention Models for\u00a0Robot Task Learning and\u00a0Execution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3226-8527","authenticated-orcid":false,"given":"Giuseppe","family":"Rauso","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8636-7628","authenticated-orcid":false,"given":"Riccardo","family":"Caccavale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-6221","authenticated-orcid":false,"given":"Alberto","family":"Finzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"18_CR1","unstructured":"Akakzia, A., Colas, C., Oudeyer, P.Y., Chetouani, M., Sigaud, O.: Grounding language to autonomously-acquired skills via goal generation. arXiv:2204.04308 (2021)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments. arXiv:1711.07280 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Learning to compose neural networks for question answering. arXiv:1601.01705 (2016)","DOI":"10.18653\/v1\/N16-1181"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. arXiv:1511.02799 (2017)","DOI":"10.1109\/CVPR.2016.12"},{"key":"18_CR5","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 (2016)"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"2229","DOI":"10.1007\/s10514-019-09876-x","volume":"43","author":"R Caccavale","year":"2019","unstructured":"Caccavale, R., Finzi, A.: Learning attentional regulations for structured tasks execution in robotic cognitive control. Auton. Robot. 43, 2229\u20132243 (2019)","journal-title":"Auton. Robot."},{"issue":"2","key":"18_CR7","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1111\/tops.12587","volume":"14","author":"R Caccavale","year":"2022","unstructured":"Caccavale, R., Finzi, A.: A robotic cognitive control framework for collaborative task execution and learning. Top. Cogn. Sci. 14(2), 327\u2013343 (2022)","journal-title":"Top. Cogn. Sci."},{"key":"18_CR8","unstructured":"Chevalier-Boisvert, M., et al.: Babyai: A platform to study the sample efficiency of grounded language learning. arXiv:1810.08272 (2019)"},{"key":"18_CR9","unstructured":"Chevalier-Boisvert, M., et al.: Minigrid & miniworld: Modular i & customizable reinforcement learning environments for goal-oriented tasks. arXiv:2306.13831 (2023)"},{"key":"18_CR10","unstructured":"Choi, J., Lee, B.J., Zhang, B.T.: Multi-focus attention network for efficient deep reinforcement learning. ArXiv abs\/1712.04603 (2017). https:\/\/api.semanticscholar.org\/CorpusID:3824441"},{"key":"18_CR11","unstructured":"Colas, C., et al.: Language as a cognitive tool to imagine goals in curiosity-driven exploration. arXiv:2002.09253 (2020)"},{"key":"18_CR12","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable mdps. arXiv:1507.06527 (2017)"},{"key":"18_CR13","doi-asserted-by":"publisher","unstructured":"Lindsay, G.W.: Attention in psychology, neuroscience, and machine learning. Front. Comput. Neurosci. 14 (2020). https:\/\/doi.org\/10.3389\/fncom.2020.00029, https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2020.00029","DOI":"10.3389\/fncom.2020.00029"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Manchin, A., Abbasnejad, E., van\u00a0den Hengel, A.: Reinforcement learning with attention that works: A self-supervised approach. arXiv:1904.03367 (2019)","DOI":"10.1007\/978-3-030-36802-9_25"},{"key":"18_CR15","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. arXiv:1406.6247 (2014)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015). https:\/\/api.semanticscholar.org\/CorpusID:205242740","DOI":"10.1038\/nature14236"},{"key":"18_CR17","unstructured":"Mott, A., Zoran, D., Chrzanowski, M., Wierstra, D., Rezende, D.J.: Towards interpretable reinforcement learning using attention augmented agents. arXiv:1906.02500 (2019)"},{"key":"18_CR18","unstructured":"Mousavi, S., Schukat, M., Howley, E., Borji, A., Mozayani, N.: Learning to predict where to look in interactive environments using deep recurrent q-learning. arXiv:1612.05753 (2017)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Conceptual reinforcement learning for language-conditioned tasks. arXiv:2303.05069 (2023)","DOI":"10.1609\/aaai.v37i8.26129"},{"key":"18_CR20","unstructured":"R\u00f6der, F., Eppe, M.: Language-conditioned reinforcement learning to solve misunderstandings with action corrections. arXiv:2211.10168 (2022)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"R\u00f6der, F., Eppe, M., Wermter, S.: Grounding hindsight instructions in multi-goal reinforcement learning for robotics. arXiv:2204.04308 (2022)","DOI":"10.1109\/ICDL53763.2022.9962207"},{"key":"18_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"18_CR23","unstructured":"Shan, M., Atanasov, N.: A spatiotemporal model with visual attention for video classification. arXiv:1707.02069 (2017)"},{"issue":"3","key":"18_CR24","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379\u2013423 (1948). https:\/\/doi.org\/10.1002\/j.1538-7305.1948.tb01338.x","journal-title":"Bell Syst. Tech. J."},{"key":"18_CR25","unstructured":"Sorokin, I., Seleznev, A., Pavlov, M., Fedorov, A., Ignateva, A.: Deep attention recurrent q-network. arXiv:1512.01693 (2015)"},{"key":"18_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv:1706.03762 (2023)"},{"key":"18_CR27","unstructured":"Zambaldi, V.F., et al.: Deep reinforcement learning with relational inductive biases. In: International Conference on Learning Representations (2018). https:\/\/api.semanticscholar.org\/CorpusID:59233950"}],"container-title":["Lecture Notes in Computer Science","AIxIA 2024 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-80607-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T17:05:11Z","timestamp":1735664711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-80607-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031806063","9783031806070"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-80607-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bolzano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}