{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:22:38Z","timestamp":1775913758335,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,9]]},"DOI":"10.1109\/smc53654.2022.9945462","type":"proceedings-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T20:49:04Z","timestamp":1668804544000},"page":"2575-2582","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Navigation Agents Using Attention-Augmented Memory"],"prefix":"10.1109","author":[{"given":"Jia","family":"Qu","sequence":"first","affiliation":[{"name":"Advanced Technology R&D Center, Mitsubishi Electric Corporation,Hyogo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shotaro","family":"Miwa","sequence":"additional","affiliation":[{"name":"Advanced Technology R&D Center, Mitsubishi Electric Corporation,Hyogo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukiyasu","family":"Domae","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Industrial Cyber-Physical Systems Research Center,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2014","journal-title":"3rd International Conference on Learning Representations ICLR 2015 - Conference Track Proceedings"},{"key":"ref10","first-page":"1475","article-title":"Reinforcement Learning Memory","author":"bakker","year":"2002","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref11","first-page":"2347","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"30th International Conference on Machine Learning ICML 2013"},{"key":"ref12","first-page":"4067","article-title":"Control of memory, active perception, and action in minecraft","volume":"6","author":"oh","year":"2016","journal-title":"ICML 2016 33rd International Conf Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01236-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00884"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","author":"parisotto","year":"2021","journal-title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation"},{"key":"ref17","first-page":"7443","article-title":"Stabilizing Transformers for Reinforcement Learning","volume":"partf168147 10","author":"parisotto","year":"2019","journal-title":"ICML 2020 37th International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2011.01.029"},{"key":"ref28","article-title":"Deep attention recurrent Q-network","author":"sorokin","year":"2015","journal-title":"arXiv preprint arXiv 1512 01882"},{"key":"ref4","first-page":"3616","article-title":"Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions","volume":"partf168147 5","author":"gottesman","year":"2020","journal-title":"ICML 2020 37th International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17235"},{"key":"ref3","first-page":"1792","article-title":"Visualizing and understanding atari agents","author":"greydanus","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref6","author":"koul","year":"2018","journal-title":"Learning Finite State Representations of Recurrent Policy Networks"},{"key":"ref29","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"5th International Conference on Learning Representations ICLR 2017 - Conference Track Proceedings"},{"key":"ref5","author":"juozapaitis","year":"2019","journal-title":"Explainable reinforcement learning via reward decomposition"},{"key":"ref8","author":"anderson","year":"2018","journal-title":"On evaluation of embodied navigation agents"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref2","author":"milani","year":"2022","journal-title":"Explainable Reinforcement Learning A Survey"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref1","article-title":"Deepmind lab","author":"beattie","year":"2016","journal-title":"arXiv preprint arXiv 1612 03801"},{"key":"ref20","first-page":"2939","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","volume":"4","author":"wang","year":"2016","journal-title":"ICML 2016 33rd International Conf Machine Learning"},{"key":"ref22","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2014","journal-title":"3rd International Conference on Learning Representations ICLR 2015 - Conference Track Proceedings"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref26","article-title":"Towards interpretable reinforcement learning using attention augmented agents","author":"mott","year":"2019","journal-title":"arXiv preprint arXiv 1906 02916"},{"key":"ref25","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Prague, Czech Republic","start":{"date-parts":[[2022,10,9]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9945068\/9945069\/09945462.pdf?arnumber=9945462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:53:37Z","timestamp":1670874817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/smc53654.2022.9945462","relation":{},"subject":[],"published":{"date-parts":[[2022,10,9]]}}}