{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T01:52:35Z","timestamp":1730253155331,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/icosc.2018.8587772","type":"proceedings-article","created":{"date-parts":[[2019,1,18]],"date-time":"2019-01-18T22:11:13Z","timestamp":1547849473000},"page":"188-193","source":"Crossref","is-referenced-by-count":0,"title":["Learning Upper-Level Policy using Importance Sampling-based Policy Search Method"],"prefix":"10.1109","author":[{"given":"Jose","family":"Pastor","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henry","family":"Diaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leopoldo","family":"Armesto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alicia","family":"Esparza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Sala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1016\/j.neunet.2009.12.004","article-title":"2010 special issue: Parameter-exploring policy gradients","volume":"23","author":"sehnke","year":"2010","journal-title":"Neural Netw"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2307\/2291224"},{"key":"ref13","first-page":"1000","article-title":"On a connection between importance sampling and the likelihood ratio policy gradient","author":"jie","year":"2010","journal-title":"Advances in neural information processing systems"},{"article-title":"A note on importance sampling using standardized weights","year":"1992","author":"kong","key":"ref14"},{"journal-title":"Generalized Linear Models and Extensions","year":"2001","author":"hardin","key":"ref15"},{"journal-title":"Neural Networks A Comprehensive Foundation","year":"1998","author":"haykin","key":"ref16"},{"key":"ref17","first-page":"155","article-title":"Support vector regression machines","author":"drucker","year":"1997","journal-title":"Advances in Neural Information Processing Systems 9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/B:STCO.0000035301.49549.88"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref6","article-title":"LQR and SMC control applied to pendular platforms","volume":"0","author":"ar\u00e9valo-castiblanco","year":"2018","journal-title":"Revista Iberoamericana de Automática e Informática Industrial"},{"journal-title":"Learning Motor Skills","year":"2016","author":"kober","key":"ref5"},{"key":"ref8","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref7","article-title":"Modeling and control of a rotational inverted pendulum applying multi-objective optimization techniques","volume":"0","author":"subia","year":"2018","journal-title":"Revista Iberoamericana de Automática e Informática Industrial"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","volume":"12","author":"wiering","year":"2012","journal-title":"Reinforcement Learning State-of-the-Art"},{"key":"ref9","article-title":"Parameters optimization applying Monte Carlo methods and evolutionary algorithms. enforcement to a trajectory tracking controller in non-linear systems","volume":"0","author":"puchol","year":"2018","journal-title":"Revista Iberoamericana de Automática e Informática Industrial"},{"key":"ref20","first-page":"1079","article-title":"Locally weighted projection regression: An o(n) algorithm for incremental real time learning in high dimensional space","author":"vijayakumar","year":"2000","journal-title":"Proceedings of the Seventeenth International Conference on Machine Learning (ICML)"}],"event":{"name":"2018 7th International Conference on Systems and Control (ICSC)","start":{"date-parts":[[2018,10,24]]},"location":"Valencia","end":{"date-parts":[[2018,10,26]]}},"container-title":["2018 7th International Conference on Systems and Control (ICSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8552602\/8587770\/08587772.pdf?arnumber=8587772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:59:30Z","timestamp":1598227170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8587772\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icosc.2018.8587772","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}