{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:43:06Z","timestamp":1729676586348,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/ssci.2016.7849370","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T22:24:33Z","timestamp":1487283873000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Robust and explorative behavior in model-based Bayesian reinforcement learning"],"prefix":"10.1109","author":[{"given":"Toru","family":"Hishinuma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Senda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553441"},{"key":"ref11","first-page":"19","article-title":"A Bayesian Sampling Approach to Exploration in Reinforcement Learning","author":"asmuth","year":"2009","journal-title":"Proc UAI"},{"journal-title":"Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration arXiv preprint arXiv 1509 06824","year":"2015","author":"xie","key":"ref12"},{"key":"ref13","first-page":"260","article-title":"Near-optimal reinforcement learning in polynomial time","author":"kearns","year":"1998","journal-title":"Proc ICML"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1613\/jair.2567","article-title":"Online Planning Algorithms for POMDPs","volume":"32","author":"ross","year":"2008","journal-title":"J Artificial Intelligence Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143932"},{"key":"ref16","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for POMDPs","volume":"3","author":"pineau","year":"2003","journal-title":"IJCAI"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1080.0685"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref3"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref5","article-title":"Neuro-Dynamic Programming","author":"bertsekas","year":"1996","journal-title":"Athena Scientific"},{"journal-title":"Bayesian Reinforcement Learning A Survey","year":"2015","author":"ghavamzadeh","key":"ref8"},{"journal-title":"Optimal Learning Computational Procedures for Bayes-adaptive Markov Decision Processes","year":"2002","author":"duff","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0657-6"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref9","first-page":"943","article-title":"A Bayesian framework for reinforcement learning","author":"strens","year":"2000","journal-title":"Proc ICML"}],"event":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2016,12,6]]},"location":"Athens, Greece","end":{"date-parts":[[2016,12,9]]}},"container-title":["2016 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7840087\/7849361\/07849370.pdf?arnumber=7849370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,24]],"date-time":"2022-07-24T09:28:27Z","timestamp":1658654907000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7849370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/ssci.2016.7849370","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}