{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:25:24Z","timestamp":1730298324325,"version":"3.28.0"},"reference-count":9,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/ssci.2016.7849367","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T22:24:33Z","timestamp":1487283873000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement learning based algorithm with Safety Handling and Risk Perception"],"prefix":"10.1109","author":[{"given":"Suhas","family":"Shyamsundar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tommaso","family":"Mannucci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik-Jan","family":"van Kampen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2514\/6.2015-1757"},{"key":"ref3","article-title":"Safe Exploration in Markov Decision Processes","author":"moldovan","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref6","article-title":"A reinforcement learning based agent navigation system","author":"zuo","year":"2014","journal-title":"IEEE Int Conf Syst Man Cybern"},{"key":"ref5","first-page":"76","article-title":"Safe reinforcement learning in high-risk tasks through policy improvement","author":"polo","year":"2011","journal-title":"Proc IEEE Intl Symp on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref7","article-title":"Q-learning for mobile agent navigation in Indoor environment","author":"tamilselvi","year":"2011","journal-title":"IEEE International Conference on Recent Trends in Information Technology"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1163\/1568553042674662"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref9"},{"key":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"}],"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\/07849367.pdf?arnumber=7849367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T22:22:31Z","timestamp":1488406951000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7849367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/ssci.2016.7849367","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}