{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T10:32:37Z","timestamp":1756463557772,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,1,7]],"date-time":"2019-01-07T00:00:00Z","timestamp":1546819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Universidad Central de Chile","award":["FIP2017030"],"award-info":[{"award-number":["FIP2017030"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,1,7]]},"DOI":"10.1145\/3309772.3309801","type":"proceedings-article","created":{"date-parts":[[2019,7,12]],"date-time":"2019-07-12T13:12:48Z","timestamp":1562937168000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Reinforcement learning using continuous states and interactive feedback"],"prefix":"10.1145","author":[{"given":"Angel","family":"Ayala","sequence":"first","affiliation":[{"name":"Universidad Central de Chile, Santiago, Chile"}]},{"given":"Claudio","family":"Henr\u00edquez","sequence":"additional","affiliation":[{"name":"Universidad Central de Chile, Santiago, Chile"}]},{"given":"Francisco","family":"Cruz","sequence":"additional","affiliation":[{"name":"Universidad Central de Chile, Santiago, Chile"}]}],"member":"320","published-online":{"date-parts":[[2019,1,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"G. Brockman V. Cheung L. Pettersson J. Schneider J. Schulman J. Tang and W. Zaremba. 2016. OpenAI Gym. ArXiv e-prints (June 2016). arXiv:1606.01540  G. Brockman V. Cheung L. Pettersson J. Schneider J. Schulman J. Tang and W. Zaremba. 2016. OpenAI Gym. ArXiv e-prints (June 2016). arXiv:1606.01540"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2832581.2832718"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2018.1443318"},{"volume-title":"4th International Conference on Development and Learning and on Epigenetic Robotics. 165--170","author":"Cruz F.","key":"e_1_3_2_1_5_1","unstructured":"F. Cruz , S. Magg , C. Weber , and S. Wermter . 2014. Improving reinforcement learning with interactive feedback and affordances . In 4th International Conference on Development and Learning and on Epigenetic Robotics. 165--170 . F. Cruz, S. Magg, C. Weber, and S. Wermter. 2014. Improving reinforcement learning with interactive feedback and affordances. In 4th International Conference on Development and Learning and on Epigenetic Robotics. 165--170."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1571643"},{"key":"e_1_3_2_1_7_1","volume-title":"BOXES: An experiment in adaptive control.","author":"Miche D.","year":"1968","unstructured":"D. Miche and R. A. Chambers . 1968 . 9 BOXES: An experiment in adaptive control. D. Miche and R. A. Chambers. 1968. 9 BOXES: An experiment in adaptive control."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1597538.1597696"},{"volume-title":"Animal intelligence","author":"Thorndike E. L.","key":"e_1_3_2_1_10_1","unstructured":"E. L. Thorndike . 1911. Animal intelligence ; experimental studies. New York , The Macmillan company , 324 pages. https:\/\/www.biodiversitylibrary.org\/item\/16001 E. L. Thorndike. 1911. Animal intelligence; experimental studies. New York, The Macmillan company, 324 pages. https:\/\/www.biodiversitylibrary.org\/item\/16001"},{"key":"e_1_3_2_1_11_1","volume-title":"A Heretical Theory. Alan M. Turing","author":"Turing A. M.","year":"1948","unstructured":"A. M. Turing . 1948. Turing , Intelligent Machinery , A Heretical Theory. Alan M. Turing ( 1948 ), 128--134. A. M. Turing. 1948. Turing, Intelligent Machinery, A Heretical Theory. Alan M. Turing (1948), 128--134."},{"volume-title":"Reinforcement Learning in Continuous Action Spaces. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 272--279","author":"van Hasselt H.","key":"e_1_3_2_1_12_1","unstructured":"H. van Hasselt and M. A. Wiering . 2007 . Reinforcement Learning in Continuous Action Spaces. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 272--279 . H. van Hasselt and M. A. Wiering. 2007. Reinforcement Learning in Continuous Action Spaces. In 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning. 272--279."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_15_1","first-page":"172","article-title":"2012. A Predictive Network Architecture for a Robust and Smooth Robot Docking Behavior","volume":"3","author":"Zhong J.","unstructured":"J. Zhong , C. Weber , and S. Wermter . 2012. A Predictive Network Architecture for a Robust and Smooth Robot Docking Behavior . Paladyn 3 (12 2012), 172 -- 180 . J. Zhong, C. Weber, and S. Wermter. 2012. A Predictive Network Architecture for a Robust and Smooth Robot Docking Behavior. Paladyn 3 (12 2012), 172--180.","journal-title":"Paladyn"}],"event":{"name":"APPIS 2019: 2nd International Conference on Applications of Intelligent Systems","acronym":"APPIS 2019","location":"Las Palmas de Gran Canaria Spain"},"container-title":["Proceedings of the 2nd International Conference on Applications of Intelligent Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3309772.3309801","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3309772.3309801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:36Z","timestamp":1750204416000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3309772.3309801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,7]]},"references-count":13,"alternative-id":["10.1145\/3309772.3309801","10.1145\/3309772"],"URL":"https:\/\/doi.org\/10.1145\/3309772.3309801","relation":{},"subject":[],"published":{"date-parts":[[2019,1,7]]},"assertion":[{"value":"2019-01-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}