{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:28:16Z","timestamp":1730262496398,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"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":[[2023,10,29]]},"DOI":"10.1109\/ieeeconf59524.2023.10477059","type":"proceedings-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T19:28:52Z","timestamp":1711999732000},"page":"1377-1380","source":"Crossref","is-referenced-by-count":0,"title":["Predictive Estimation for Reinforcement Learning with Time-Varying Reward Functions"],"prefix":"10.1109","author":[{"given":"Abolfazl","family":"Hashemi","sequence":"first","affiliation":[{"name":"Purdue University,Dept. of Electrical and Computer Engineering,West Lafatyette,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antesh","family":"Upadhyay","sequence":"additional","affiliation":[{"name":"Purdue University,Dept. of Electrical and Computer Engineering,West Lafatyette,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1583","article-title":"Online learning in episodic Markovian decision processes by relative entropy policy search","volume-title":"Proceedings of Advances in neural information processing systems (NeurIPS)","author":"Zimin","year":"2013"},{"key":"ref2","volume-title":"Dynamic programming and optimal control","volume":"1","author":"Bertsekas","year":"1995"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cdc.1995.478953"},{"volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","year":"2014","author":"Puterman","key":"ref4"},{"journal-title":"Large-scale Markov decision problems via the linear programming dual","year":"2019","author":"Abbasi-Yadkori","key":"ref5"},{"journal-title":"Primal-dual \u03c0 learning: Sample complexity and sublinear run time for ergodic Markov decision problems","year":"2017","author":"Wang","key":"ref6"},{"key":"ref7","first-page":"5478","article-title":"Online convex optimization in adversarial Markov decision processes","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Rosenberg","year":"2019"},{"key":"ref8","first-page":"2337","article-title":"Large scale Markov decision processes with changing rewards","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Cardoso","year":"2019"},{"key":"ref9","first-page":"805","article-title":"The adversarial stochastic shortest path problem with unknown transition probabilities","volume-title":"Proceedings of Artificial Intelligence and Statistics (AISTATS)","author":"Neu","year":"2012"},{"key":"ref10","first-page":"512","article-title":"Online learning in Markov decision processes with changing cost sequences","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Dick","year":"2014"},{"journal-title":"Learning adversarial MDPs with bandit feedback and unknown transition","year":"2019","author":"Jin","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483085"},{"key":"ref13","first-page":"993","article-title":"Online learning with predictable sequences","volume-title":"Conference on Learning Theory","author":"Rakhlin","year":"2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"}],"event":{"name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2023,10,29]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2023,11,1]]}},"container-title":["2023 57th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10476702\/10476779\/10477059.pdf?arnumber=10477059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T05:11:11Z","timestamp":1712034671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10477059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf59524.2023.10477059","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]}}}