{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:16:33Z","timestamp":1740122193483,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,1,13]],"date-time":"2020-01-13T00:00:00Z","timestamp":1578873600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,13]],"date-time":"2020-01-13T00:00:00Z","timestamp":1578873600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000003","name":"Boeing","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000003","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007297","name":"Office of Naval Research Global","doi-asserted-by":"publisher","award":["MURI Grant N000141110688"],"award-info":[{"award-number":["MURI Grant N000141110688"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IBM"},{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","award":["Machine Learning Research Awards program"],"award-info":[{"award-number":["Machine Learning Research Awards program"]}],"id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BRC","award":["Grant N000141712072"],"award-info":[{"award-number":["Grant N000141712072"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1007\/s10458-019-09439-5","type":"journal-article","created":{"date-parts":[[2020,1,13]],"date-time":"2020-01-13T12:02:57Z","timestamp":1578916977000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Crossmodal attentive skill learner: learning in Atari and beyond with audio\u2013video inputs"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5342-1197","authenticated-orcid":false,"given":"Dong-Ki","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shayegan","family":"Omidshafiei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Pazis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,13]]},"reference":[{"key":"9439_CR1","unstructured":"Al-Shedivat, M., Bansal, T., Burda, Y., Sutskever, I., Mordatch, I., & Abbeel, P. (2018). Continuous adaptation via meta-learning in nonstationary and competitive environments. In International Conference on Learning Representations (ICLR)."},{"key":"9439_CR2","doi-asserted-by":"crossref","unstructured":"Alvis, C. D., Ott, L., & Ramos, F. (2017). Online learning for scene segmentation with laser-constrained CRFs. International Conference on Robotics and Automation (ICRA), 4639\u20134643.","DOI":"10.1109\/ICRA.2017.7989539"},{"key":"9439_CR3","unstructured":"Andreas, J., Klein, D., & Levine, S. (2016). Modular multitask reinforcement learning with policy sketches. arXiv preprint arXiv:1611.01796."},{"key":"9439_CR4","unstructured":"Ba, J., Mnih, V., & Kavukcuoglu, K. (2014). Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755."},{"key":"9439_CR5","unstructured":"Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., & Kautz, J. (2017). Reinforcement learning through asynchronous advantage actor-critic on a GPU. In International Conference on Learning Representations (ICLR)."},{"key":"9439_CR6","unstructured":"Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473."},{"key":"9439_CR7","doi-asserted-by":"crossref","unstructured":"Beal, M. J., Attias, H., & Jojic, N. (2002). Audio-video sensor fusion with probabilistic graphical models. European Conference on Computer Vision (ECCV), 736\u2013750.","DOI":"10.1007\/3-540-47969-4_49"},{"key":"9439_CR8","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013). The arcade learning environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 47, 253\u2013279.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9439_CR9","unstructured":"Bengio, S. (2002). An asynchronous hidden markov model for audio-visual speech recognition. Advances in Neural Information Processing Systems (NIPS), 1237\u20131244."},{"key":"9439_CR10","doi-asserted-by":"crossref","unstructured":"Cadena, C., & Ko\u0161eck\u00e1, J. (2014). Semantic segmentation with heterogeneous sensor coverages. International Conference on Robotics and Automation (ICRA), 2639\u20132645.","DOI":"10.1109\/ICRA.2014.6907237"},{"key":"9439_CR11","unstructured":"Caglayan, O., Barrault, L., & Bougares, F. (2016). Multimodal attention for neural machine translation. arXiv preprint arXiv:1609.03976."},{"issue":"13","key":"9439_CR12","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1016\/j.visres.2011.04.012","volume":"51","author":"M Carrasco","year":"2011","unstructured":"Carrasco, M. (2011). Visual attention: The past 25 years. Vision research, 51(13), 1484\u20131525.","journal-title":"Vision research"},{"key":"9439_CR13","doi-asserted-by":"crossref","unstructured":"Chambers, A.\u00a0D., Scherer, S., Yoder, L., Jain, S., Nuske, S.\u00a0T., & Singh, S. (2014). Robust multi-sensor fusion for micro aerial vehicle navigation in GPS-degraded\/denied environments. In American Control Conference (ACC).","DOI":"10.1109\/ACC.2014.6859341"},{"key":"9439_CR14","unstructured":"Da\u00a0Silva, B., Konidaris, G., & Barto, A. (2012). Learning parameterized skills. arXiv preprint arXiv:1206.6398."},{"key":"9439_CR15","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.\u00a0T., Spinello, L., Riedmiller, M., & Burgard, W. (2015). Multimodal deep learning for robust RGB-D object recognition. In International Conference on Intelligent Robots and Systems (IROS).","DOI":"10.1109\/IROS.2015.7353446"},{"key":"9439_CR16","unstructured":"Harb, J., Bacon, P.-L., Klissarov, M., & Precup, D. (2017). When waiting is not an option: Learning options with a deliberation cost. arXiv preprint arXiv:1709.04571."},{"key":"9439_CR17","unstructured":"Hausknecht, M., & Stone, P. (2015). Deep recurrent Q-learning for partially observable MDPs. arXiv preprint arXiv:1507.06527."},{"key":"9439_CR18","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep residual learning for image recognition. CoRR, arXiv:1512.03385."},{"issue":"8","key":"9439_CR19","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"issue":"1","key":"9439_CR20","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998). Planning and acting in partially observable stochastic domains. Artificial Intelligence, 101(1), 99\u2013134.","journal-title":"Artificial Intelligence"},{"key":"9439_CR21","unstructured":"Kiros, R., Salakhutdinov, R., & Zemel, R.\u00a0S. (2014). Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539."},{"key":"9439_CR22","unstructured":"Konidaris, G., & Barto, A. G. (2009). Skill discovery in continuous reinforcement learning domains using skill chaining. Advances in Neural Information Processing Systems (NIPS), 1015\u20131023."},{"key":"9439_CR23","unstructured":"Kulkarni, T. D., Narasimhan, K., Saeedi, A., & Tenenbaum, J. (2016). Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. Advances in Neural Information Processing Systems (NIPS), 3675\u20133683."},{"key":"9439_CR24","unstructured":"Lafferty, J. D., McCallum, A., & Pereira, F. C. N. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. International Conference on Machine Learning (ICML), 282\u2013289."},{"issue":"2","key":"9439_CR25","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.neuron.2016.12.040","volume":"93","author":"YC Leong","year":"2017","unstructured":"Leong, Y. C., Radulescu, A., Daniel, R., DeWoskin, V., & Niv, Y. (2017). Dynamic interaction between reinforcement learning and attention in multidimensional environments. Neuron, 93(2), 451\u2013463.","journal-title":"Neuron"},{"key":"9439_CR26","unstructured":"Luong, M.-T., Pham, H., & Manning, C.\u00a0D. (2015). Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025."},{"key":"9439_CR27","doi-asserted-by":"crossref","unstructured":"Lynen, S., Achtelik, M. W., Weiss, S., Chli, M., & Siegwart, R. (2013). A robust and modular multi-sensor fusion approach applied to mav navigation. International Conference on Intelligent Robots and Systems (IROS), 3923\u20133929.","DOI":"10.1109\/IROS.2013.6696917"},{"key":"9439_CR28","unstructured":"Machado, M.\u00a0C., Bellemare, M.\u00a0G., & Bowling, M. (2017). A laplacian framework for option discovery in reinforcement learning. arXiv preprint arXiv:1703.00956."},{"issue":"4","key":"9439_CR29","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1037\/h0076778","volume":"82","author":"NJ Mackintosh","year":"1975","unstructured":"Mackintosh, N. J. (1975). A theory of attention: Variations in the associability of stimuli with reinforcement. Psychological Review, 82(4), 276.","journal-title":"Psychological Review"},{"key":"9439_CR30","unstructured":"Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., et al. (2016). Asynchronous methods for deep reinforcement learning. International Conference on Machine Learning (ICML), 1928\u20131937."},{"key":"9439_CR31","unstructured":"Mnih, V., Heess, N., Graves, A., et al. (2014). Recurrent models of visual attention. Advances in Neural Information Processing Systems (NIPS), 2204\u20132212."},{"issue":"7540","key":"9439_CR32","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529\u2013533.","journal-title":"Nature"},{"key":"9439_CR33","unstructured":"Nachum, O., Gu, S. S., Lee, H., & Levine, S. (2018). Data-efficient hierarchical reinforcement learning. Advances in Neural Information Processing Systems (NIPS), 3306\u20133317."},{"key":"9439_CR34","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. International Conference on Machine Learning (ICML), 689\u2013696."},{"issue":"21","key":"9439_CR35","doi-asserted-by":"publisher","first-page":"8145","DOI":"10.1523\/JNEUROSCI.2978-14.2015","volume":"35","author":"Y Niv","year":"2015","unstructured":"Niv, Y., Daniel, R., Geana, A., Gershman, S. J., Leong, Y. C., Radulescu, A., et al. (2015). Reinforcement learning in multidimensional environments relies on attention mechanisms. Journal of Neuroscience, 35(21), 8145\u20138157.","journal-title":"Journal of Neuroscience"},{"key":"9439_CR36","unstructured":"Nobili, S., Camurri, M., Barasuol, V., Focchi, M., Caldwell, D.\u00a0G., Semini, C., & Fallon, M. (2017). Heterogeneous sensor fusion for accurate state estimation of dynamic legged robots. In Robotics: Science and Systems (RSS)."},{"issue":"6","key":"9439_CR37","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1037\/0033-295X.87.6.532","volume":"87","author":"JM Pearce","year":"1980","unstructured":"Pearce, J. M., & Hall, G. (1980). A model for pavlovian learning: Variations in the effectiveness of conditioned but not of unconditioned stimuli. Psychological Review, 87(6), 532.","journal-title":"Psychological Review"},{"key":"9439_CR38","unstructured":"Pearce, J.\u00a0M., & Mackintosh, N.\u00a0J. (2010). Two theories of attention: A review and a possible integration. Attention and Associative Learning: From Brain to Behaviour, pages 11\u201339."},{"issue":"7676","key":"9439_CR39","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., et al. (2017). Mastering the game of go without human knowledge. Nature, 550(7676), 354\u2013359.","journal-title":"Nature"},{"key":"9439_CR40","unstructured":"Sorokin, I., Seleznev, A., Pavlov, M., Fedorov, A., & Ignateva, A. (2015). Deep attention recurrent Q-network. arXiv preprint arXiv:1512.01693."},{"key":"9439_CR41","first-page":"2949","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., & Salakhutdinov, R. (2014). Multimodal learning with deep boltzmann machines. Journal of Machine Learning Research, 15, 2949\u20132980.","journal-title":"Journal of Machine Learning Research"},{"key":"9439_CR42","doi-asserted-by":"crossref","unstructured":"Sutton, R.\u00a0S., & Barto, A.\u00a0G. (1998). Reinforcement learning: An introduction.","DOI":"10.1109\/TNN.1998.712192"},{"issue":"1\u20132","key":"9439_CR43","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. (1999). Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112(1\u20132), 181\u2013211.","journal-title":"Artificial Intelligence"},{"key":"9439_CR44","unstructured":"Vezhnevets, A.\u00a0S., Osindero, S., Schaul, T., Heess, N., Jaderberg, M., Silver, D., & Kavukcuoglu, K. (2017). Feudal networks for hierarchical reinforcement learning. arXiv preprint arXiv:1703.01161."},{"key":"9439_CR45","unstructured":"Vinyals, O., Kaiser, \u0141., Koo, T., Petrov, S., Sutskever, I., & Hinton, G. (2015). Grammar as a foreign language. Advances in Neural Information Processing Systems (NIPS), 2773\u20132781."},{"key":"9439_CR46","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A.\u00a0J., & Hovy, E.\u00a0H. (2016). Hierarchical attention networks for document classification. In North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pages 1480\u20131489."},{"key":"9439_CR47","unstructured":"Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., & Fei-Fei, L. (2015). Every moment counts: Dense detailed labeling of actions in complex videos. International Journal of Computer Vision, 1\u201315."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-019-09439-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-019-09439-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-019-09439-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T22:01:08Z","timestamp":1610488868000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-019-09439-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,13]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["9439"],"URL":"https:\/\/doi.org\/10.1007\/s10458-019-09439-5","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"type":"print","value":"1387-2532"},{"type":"electronic","value":"1573-7454"}],"subject":[],"published":{"date-parts":[[2020,1,13]]},"assertion":[{"value":"13 January 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"16"}}