{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:34:38Z","timestamp":1730266478030,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892913","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Coarse-grained Pre-guided Attention to Assist Fine-grained Attention Reinforcement Learning Agents"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Liu","sequence":"first","affiliation":[{"name":"Renmin University of China,School of Statistics,Beijing,China"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Language Understanding Lab Samsung Research China,Beijing,China"}]},{"given":"Xingrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Statistics,Beijing,China"}]},{"given":"Hanfang","family":"Yang","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Statistics,Beijing,China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2845370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/rs13112067"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.152"},{"key":"ref30","article-title":"A spatiotemporal model with visual attention for video classification","author":"shan","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11263"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00372"},{"key":"ref35","article-title":"Lebp-language expectation & binding policy: A two-stream framework for embodied vision-and-language interaction task learning agents","author":"liu","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00141"},{"key":"ref10","article-title":"Human learning in atari","author":"tsividis","year":"0","journal-title":"2017 AAAI Spring Symposium Series"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3484"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep rein-forcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Re-inforcement learning through asynchronous advantage actor-critic on a gpu","author":"babaeizadeh","year":"2016","journal-title":"ICLRE"},{"key":"ref28","article-title":"Teaching machines to read and com-prehend","author":"hermann","year":"2015","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Selective particle attention: Visual feature-based attention in deep reinforcement learning","author":"blakeman","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref3","article-title":"Multi-focus attention network for efficient deep reinforcement learning","author":"choi","year":"2017","journal-title":"ArXiv Preprint"},{"journal-title":"Focus of attention in reinforcement learning","year":"2007","author":"li","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref5","article-title":"Deep attention recurrent q-network","author":"sorokin","year":"2015","journal-title":"CoRR abs\/1512 01693"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_25"},{"key":"ref7","first-page":"12329","article-title":"Towards interpretable reinforcement learning using attention augmented agents","author":"mott","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32 Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref9","article-title":"Learning to predict where to look in interactive environments using deep recurrent q-learning","author":"mousavi","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref20","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref21","article-title":"Impala: Scalable dis-tributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278776"},{"key":"ref23","article-title":"Part-guided attention learning for vehicle instance retrieval","author":"zhang","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref26","article-title":"Arface: attention-aware and regularization for face recognition with reinforcement learning","author":"zhang","year":"2021","journal-title":"IEEE Transactions on Biometrics Behavior and Identity Science"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2978-14.2015"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892913.pdf?arnumber=9892913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:59:42Z","timestamp":1667516382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892913","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}