{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T05:02:55Z","timestamp":1750395775157,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8460180","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"6469-6475","source":"Crossref","is-referenced-by-count":5,"title":["Q-CP: Learning Action Values for Cooperative Planning"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Riccio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Capobianco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1177\/0278364913495721"},{"key":"ref11","first-page":"189","article-title":"Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks","author":"nikolaidis","year":"2015","journal-title":"2007 2nd ACM\/IEEE International Conference on Human-Robot Interaction (HRI) HRI"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/s12369-015-0310-2"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref14","first-page":"1648","article-title":"Constructing abstraction hierarchies using a skill-symbol loop","author":"konidaris","year":"2016","journal-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence ser IJCAI'16"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1613\/jair.639"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1145\/375735.376302"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/SISY.2008.4664909"},{"key":"ref18","volume":"abs 1606 3137","author":"hadfield-menell","year":"2016","journal-title":"Cooperative inverse reinforcement learning"},{"key":"ref19","volume":"abs 1401 3460","author":"bernstein","year":"2014","journal-title":"Policy iteration for decentralized control of markov decision processes"},{"year":"2014","author":"ross","journal-title":"Reinforcement and imitation learning via interactive no-regret learning","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/11871842_29","article-title":"Bandit based monte-carlo planning","author":"kocsis","year":"2006","journal-title":"Machine Learning ECML 2006"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1214\/aos\/1176344136"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref6","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1145\/1273496.1273531"},{"key":"ref5","first-page":"1","article-title":"Reinforcement learning with a gaussian mixture model","author":"agostini","year":"2010","journal-title":"The 2010 International Joint Conference on Neural Networks"},{"key":"ref8","first-page":"89","article-title":"Convergence problems of general-sum multiagent reinforcement learning","author":"bowling","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref7","first-page":"25","article-title":"Monte-carlo tree search solver","author":"winands","year":"2008","journal-title":"Proceedings of the 6th International Conference on Computers and Games ser CG '08"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/s10994-012-5280-0"},{"key":"ref9","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proceedings of the Fifteenth National\/Tentn Conference on Artificial Intelligence\/Innovative Applications of Artificial Intelligence ser AAAI'98\/IAAI'98"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref20","first-page":"681","article-title":"Solving multi agent assignment markov decision processes","author":"proper","year":"2009","journal-title":"Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/JAS.2014.7004680"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/1102351.1102377"},{"key":"ref24","first-page":"3576","article-title":"An analysis of monte carlo tree search","author":"james","year":"2017","journal-title":"AAAI"},{"key":"ref23","first-page":"1856","article-title":"Monte-carlo tree search and rapid action value estimation in computer go","volume":"175","author":"gelly","year":"2011","journal-title":"Artif In tell"},{"key":"ref26","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2018,5,21]]},"location":"Brisbane, QLD","end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08460180.pdf?arnumber=8460180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:12:19Z","timestamp":1598242339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8460180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8460180","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}