{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:38:55Z","timestamp":1740101935136,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10155973","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T17:48:03Z","timestamp":1688406483000},"page":"4555-4560","source":"Crossref","is-referenced-by-count":1,"title":["On the Benefits of Leveraging Structural Information in Planning Over the Learned Model"],"prefix":"10.23919","author":[{"given":"Jiajun","family":"Shen","sequence":"first","affiliation":[{"name":"Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kananart","family":"Kuwaranancharoen","sequence":"additional","affiliation":[{"name":"Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raid","family":"Ayoub","sequence":"additional","affiliation":[{"name":"Intel Corporation,Hillsboro,OR,USA,97124"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pietro","family":"Mercati","sequence":"additional","affiliation":[{"name":"Intel Corporation,Hillsboro,OR,USA,97124"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shreyas","family":"Sundaram","sequence":"additional","affiliation":[{"name":"Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Model-based reinforcement learning for atari. arxiv","year":"2019","author":"Kaiser","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919665"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5368-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975031.50"},{"issue":"6","key":"ref6","article-title":"Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems","volume":"7","author":"Even-Dar","year":"2006","journal-title":"Journal of machine learning research"},{"key":"ref7","article-title":"Reinforcement learning with a near optimal rate of convergence","author":"Azar","year":"2011","journal-title":"INRIA, Tech. Rep."},{"key":"ref8","first-page":"23 009","article-title":"Sample-efficient reinforcement learning for linearly-parameterized mdps with a generative model","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"6995","article-title":"Sample-optimal parametric q-learning using linearly additive features","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref10","first-page":"67","article-title":"Model-based reinforcement learning with a generative model is minimax optimal","volume-title":"Conference on Learning Theory","author":"Agarwal"},{"volume-title":"On the sample complexity of reinforcement learning.","year":"2003","author":"Kakade","key":"ref11"},{"key":"ref12","article-title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","author":"Szita","year":"2010","journal-title":"ICML"},{"key":"ref13","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"21","author":"Auer","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2225"},{"article-title":"Model-free representation learning and exploration in low-rank mdps","year":"2021","author":"Modi","key":"ref15"},{"key":"ref16","first-page":"26 517","article-title":"Efficient reinforcement learning in block mdps: A model-free representation learning approach","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_26"},{"volume-title":"Dynamic programming and markov processes.","year":"1960","author":"Howard","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10155973"},{"key":"ref21","first-page":"1432","article-title":"Hidden parameter markov decision processes: A semiparametric regression approach for discovering latent task parametrizations","volume-title":"IJCAI: proceedings of the conference","volume":"2016","author":"Doshi-Velez"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5989"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11065"}],"event":{"name":"2023 American Control Conference (ACC)","start":{"date-parts":[[2023,5,31]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10155973.pdf?arnumber=10155973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:09:36Z","timestamp":1705021776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":23,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10155973","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}