{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:51Z","timestamp":1740101751036,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004375","name":"Tel Aviv University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004375","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095643","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Energy Regularized RNNS for solving non-stationary Bandit problems"],"prefix":"10.1109","author":[{"given":"Michael","family":"Rotman","sequence":"first","affiliation":[{"name":"Tel Aviv University,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[{"name":"Tel Aviv University,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Combinatorial sleeping bandits with fairness constraints","author":"li","year":"2019","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"ref12","article-title":"Sleeping experts and bandits with stochastic action availability and adversarial rewards","author":"kanade","year":"2009","journal-title":"Int Conf on Artificial Intelligence and Statistics"},{"article-title":"Multi-armed bandit strategies for non-stationary reward distributions and delayed feedback processes","year":"2019","author":"liu","key":"ref15"},{"key":"ref14","article-title":"Rotting bandits are no harder than stochastic ones","author":"seznec","year":"2019","journal-title":"Int Conf on AI and Statistics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4024"},{"key":"ref10","article-title":"Decision transformer: Reinforcement learning via sequence modeling","author":"chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref2","first-page":"3074","article-title":"Rotting bandits","author":"levine","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref17","article-title":"Efficient contextual bandits in non- stationary worlds","author":"luo","year":"2018","journal-title":"COLT"},{"key":"ref16","article-title":"A contextual-bandit approach to personalized news article recommendation","author":"li","year":"2010","journal-title":"World Wide Web"},{"key":"ref19","first-page":"2388","article-title":"Contextual semibandits via supervised learning oracles","author":"krishnamurthy","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Achieving optimal dynamic regret for non-stationary bandits without prior information","author":"auer","year":"2019","journal-title":"COLT"},{"article-title":"Adapting multi-armed bandits policies to contextual bandits scenarios","year":"2018","author":"cortes","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref26","article-title":"Rmsprop and equilibrated adaptive learning rates for nonconvex optimization","author":"bengio","year":"2015","journal-title":"corr abs\/1502 04390"},{"article-title":"Deep bayesian bandits showdown: An empirical comparison of bayesian deep networks for thompson sampling","year":"2018","author":"riquelme","key":"ref25"},{"article-title":"Efficient exploration in reinforcement learning","year":"1992","author":"thrun","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref21","article-title":"Neural contextual bandits with ucb-based exploration","author":"zhou","year":"2020","journal-title":"ICML"},{"article-title":"Online bandit learning against an adaptive adversary: from regret to policy regret","year":"2012","author":"arora","key":"ref28"},{"key":"ref27","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"NIPS"},{"key":"ref8","article-title":"Tracking the best expert in non-stationary stochastic environments","author":"wei","year":"2016","journal-title":"NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-017-0050-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849366"},{"key":"ref3","article-title":"The epoch-greedy algorithm for contextual multi-armed bandits","author":"langford","year":"2007","journal-title":"NIPS"},{"key":"ref6","article-title":"Stochas- tic multi-armed-bandit problem with non-stationary rewards","author":"besbes","year":"2014","journal-title":"NIPS"},{"key":"ref5","article-title":"Overcoming catastrophic forgetting with hard attention to the task","author":"serra","year":"2018","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095643.pdf?arnumber=10095643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:10Z","timestamp":1699902190000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095643","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}