{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T23:37:10Z","timestamp":1768001830478,"version":"3.49.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030368012","type":"print"},{"value":"9783030368029","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36802-9_25","type":"book-chapter","created":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T18:03:03Z","timestamp":1575568983000},"page":"223-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["Reinforcement Learning with Attention that Works: A Self-Supervised Approach"],"prefix":"10.1007","author":[{"given":"Anthony","family":"Manchin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Abbasnejad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"van den Hengel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,12,5]]},"reference":[{"key":"25_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). CoRR abs\/1409.0473. http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"25_CR2","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.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"25_CR3","doi-asserted-by":"publisher","DOI":"10.1037\/10037-000","volume-title":"Perception and communication","author":"D. E. Broadbent","year":"1958","unstructured":"Broadbent, D.E.: Perception and Communication (1958)"},{"key":"25_CR4","unstructured":"Choi, J., Lee, B., Zhang, B.: Multi-focus attention network for efficient deep reinforcement learning. CoRR abs\/1712.04603 (2017). http:\/\/arxiv.org\/abs\/1712.04603"},{"key":"25_CR5","unstructured":"Dhariwal, P., et al.: Openai baselines (2017). https:\/\/github.com\/openai\/baselines"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Fang, S., Xie, H., Zha, Z.J., Sun, N., Tan, J., Zhang, Y.: Attention and language ensemble for scene text recognition with convolutional sequence modeling. In: Proceedings of the 26th ACM International Conference on Multimedia, MM 2018, pp. 248\u2013256. ACM, New York (2018). https:\/\/doi.org\/10.1145\/3240508.3240571","DOI":"10.1145\/3240508.3240571"},{"key":"25_CR7","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. CoRR abs\/1706.10295 (2017). http:\/\/arxiv.org\/abs\/1706.10295"},{"key":"25_CR8","doi-asserted-by":"publisher","unstructured":"Gregor, M., Nemec, D., Janota, A., Pirnik, R.: A visual attention operator for playing Pac-Man, pp. 1\u20136, May 2018. https:\/\/doi.org\/10.1109\/ELEKTRO.2018.8398308","DOI":"10.1109\/ELEKTRO.2018.8398308"},{"key":"25_CR9","unstructured":"Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. CoRR abs\/1711.00138 (2017). http:\/\/arxiv.org\/abs\/1711.00138"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Han, Y.: Explore multi-step reasoning in video question answering. In: Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild. p. 5. CoVieW 2018. ACM, New York (2018). https:\/\/doi.org\/10.1145\/3265987.3265996","DOI":"10.1145\/3265987.3265996"},{"key":"25_CR11","unstructured":"Hausknecht, M.J., Stone, P.: Deep recurrent q-learning for partially observable mdps. CoRR abs\/1507.06527 (2015). http:\/\/arxiv.org\/abs\/1507.06527"},{"key":"25_CR12","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. CoRR abs\/1803.00933 (2018). http:\/\/arxiv.org\/abs\/1803.00933"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Kastaniotis, D., Ntinou, I., Tsourounis, D., Economou, G., Fotopoulos, S.: Attention-aware generative adversarial networks (ATA-GANS). CoRR abs\/1802.09070 (2018). http:\/\/arxiv.org\/abs\/1802.09070","DOI":"10.1109\/IVMSPW.2018.8448850"},{"key":"25_CR14","unstructured":"Kay, W., et al.: The kinetics human action video dataset. CoRR abs\/1705.06950 (2017). http:\/\/arxiv.org\/abs\/1705.06950"},{"key":"25_CR15","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. CoRR abs\/1406.6247 (2014). http:\/\/arxiv.org\/abs\/1406.6247"},{"issue":"7540","key":"25_CR16","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"25_CR17","unstructured":"Oh, J., Chockalingam, V., Singh, S.P., Lee, H.: Control of memory, active perception, and action in minecraft. CoRR abs\/1605.09128 (2016). http:\/\/arxiv.org\/abs\/1605.09128"},{"key":"25_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017). http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"25_CR19","unstructured":"Shi, J., Zhang, H., Li, J.: Explainable and explicit visual reasoning over scene graphs. CoRR abs\/1812.01855 (2018). http:\/\/arxiv.org\/abs\/1812.01855"},{"key":"25_CR20","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. CoRR abs\/1604.01753 (2016). http:\/\/arxiv.org\/abs\/1604.01753"},{"key":"25_CR21","unstructured":"Sorokin, I., Seleznev, A., Pavlov, M., Fedorov, A., Ignateva, A.: Deep attention recurrent q-network. CoRR abs\/1512.01693 (2015). http:\/\/arxiv.org\/abs\/1512.01693"},{"key":"25_CR22","unstructured":"Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. CoRR abs\/1711.07971 (2017). http:\/\/arxiv.org\/abs\/1711.07971"},{"key":"25_CR23","unstructured":"Wu, Y., Mansimov, E., Grosse, R.B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 5279\u20135288. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/7112-scalable-trust-region-method-for-deep-reinforcement-learning-using-kronecker-factored-approximation.pdf"},{"key":"25_CR24","unstructured":"Xu, T., et al.: AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks. CoRR abs\/1711.10485 (2017). http:\/\/arxiv.org\/abs\/1711.10485"},{"key":"25_CR25","unstructured":"Yuezhang, L., Zhang, R., Ballard, D.H.: An initial attempt of combining visual selective attention with deep reinforcement learning. CoRR abs\/1811.04407 (2018). http:\/\/arxiv.org\/abs\/1811.04407"},{"key":"25_CR26","unstructured":"Zhang, R., et al.: AGIL: learning attention from human for visuomotor tasks. CoRR abs\/1806.03960 (2018). http:\/\/arxiv.org\/abs\/1806.03960"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, S., Zhang, Z.: Attention-via-attention neural machine translation (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16534","DOI":"10.1609\/aaai.v32i1.11254"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36802-9_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:51:26Z","timestamp":1710262286000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-36802-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030368012","9783030368029"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36802-9_25","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"5 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}