{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:13:13Z","timestamp":1771330393061,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160946","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T13:20:56Z","timestamp":1688476856000},"page":"7140-7146","source":"Crossref","is-referenced-by-count":14,"title":["Learning to View: Decision Transformers for Active Object Detection"],"prefix":"10.1109","author":[{"given":"Wenhao","family":"Ding","sequence":"first","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA,94098"}]},{"given":"Nathalie","family":"Majcherczyk","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA,94098"}]},{"given":"Mohit","family":"Deshpande","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA,94098"}]},{"given":"Xuewei","family":"Qi","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA,94098"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA,15213"}]},{"given":"Rajasimman","family":"Madhivanan","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA,94098"}]},{"given":"Arnie","family":"Sen","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA,94098"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"kolve","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2019.00019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"ref34","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"nair","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref37","author":"paszke","year":"2017","journal-title":"Automatic differentiation in pytorch"},{"key":"ref14","article-title":"Online decision transformer","author":"zheng","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref36","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref31","article-title":"Offline reinforcement learning with implicit q-learning","author":"kostrikov","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref30","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"kumar","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00213"},{"key":"ref33","article-title":"Don't change the algorithm, change the data: Exploratory data for offline reinforcement learning","author":"yarats","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref10","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","author":"agarwal","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2890849"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref19","article-title":"Move to see better: Self-improving embodied object detection","author":"fang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Transfer learning with causal counterfactual reasoning in decision transformers","author":"boustati","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"You can't count on luck: Why decision transformers fail in stochastic environments","author":"paster","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Generalized decision transformer for offline hindsight information matching","author":"furuta","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref22","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref28","article-title":"Generalizing goal-conditioned reinforcement learning with variational causal reasoning","author":"ding","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"A survey on offline reinforcement learning: Taxonomy, review, and open problems","author":"prudencio","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340696"},{"key":"ref9","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"fu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0179-3"},{"key":"ref3","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840991"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160946.pdf?arnumber=10160946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T13:36:20Z","timestamp":1690205780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160946\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160946","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}