{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:07:55Z","timestamp":1725484075427},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1109\/devlrn.2014.6982960","type":"proceedings-article","created":{"date-parts":[[2014,12,30]],"date-time":"2014-12-30T23:48:19Z","timestamp":1419983299000},"page":"93-100","source":"Crossref","is-referenced-by-count":5,"title":["Learning from human reward benefits from socio-competitive feedback"],"prefix":"10.1109","author":[{"given":"Guangliang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hayley","family":"Hung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. Bradley","family":"Knox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"Gamification: Toward a definition","author":"deterding","year":"2011","journal-title":"CHI 2011 Gamification Workshop"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753589"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1145\/1557914.1557948"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1177\/1745691612442904"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/1452520.1452527"},{"key":"13","article-title":"Transparency and socially guided machine learning","author":"thomaz","year":"2006","journal-title":"ICDL"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/1734454.1734562"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0163-x"},{"key":"12","article-title":"Real-time interactive reinforcement learning for robots","author":"thomaz","year":"2005","journal-title":"AAAI Workshop"},{"journal-title":"The Gamification of Learning and Instruction Game-based Methods and Strategies for Training and Education","year":"2012","author":"kapp","key":"21"},{"journal-title":"Game-Based Marketing Inspire Customer Loyalty Through Rewards Challenges and Contests","year":"2010","author":"zichermann","key":"20"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2012.12.020"},{"key":"23","article-title":"Learning non-myopically from humangenerated reward","author":"knox","year":"2013","journal-title":"IUI"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"24"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45071-8_36"},{"journal-title":"Learning from Human-generated Reward","year":"2012","author":"knox","key":"26"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"27"},{"key":"28","article-title":"Evolving a heuristic function for the game of Tetris","author":"bohm","year":"2004","journal-title":"Proc Lernen Wissensentdeckung und Adaptivitat LWA"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.12.2936"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376334"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343862"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"7","article-title":"Using informative behavior to increase engagement in the tamer framework","author":"li","year":"2013","journal-title":"AAMAS"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228725"},{"key":"5","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","author":"thomaz","year":"2006","journal-title":"Proc of the National Conference on AI"},{"key":"4","article-title":"Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression","author":"maclin","year":"2005","journal-title":"National Conference on Artificial Intelligence"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16952-6_49"}],"event":{"name":"2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob)","start":{"date-parts":[[2014,10,13]]},"location":"Genoa, Italy","end":{"date-parts":[[2014,10,16]]}},"container-title":["4th International Conference on Development and Learning and on Epigenetic Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6971976\/6982939\/06982960.pdf?arnumber=6982960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:19:05Z","timestamp":1602688745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6982960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2014.6982960","relation":{},"subject":[],"published":{"date-parts":[[2014,10]]}}}