{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:49:32Z","timestamp":1729640972852,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/humanoids.2017.8246959","type":"proceedings-article","created":{"date-parts":[[2018,1,8]],"date-time":"2018-01-08T22:46:08Z","timestamp":1515451568000},"page":"771-776","source":"Crossref","is-referenced-by-count":5,"title":["Deep reinforcement learning for conversational robots playing games"],"prefix":"10.1109","author":[{"given":"Heriberto","family":"Cuayahuitl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref12","article-title":"End-to-end training of deep visuomotor policies","volume":"abs 1504 702","author":"levine","year":"2015","journal-title":"CoRR"},{"key":"ref13","article-title":"A review of verbal and non-verbal human-robot interactive communication","volume":"abs 1401 4994","author":"mavridis","year":"2014","journal-title":"CoRR"},{"key":"ref14","article-title":"Asynchronous methods for deep reinforcement learning","volume":"abs 1602 1783","author":"mnih","year":"2016","journal-title":"CoRR"},{"key":"ref15","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","article-title":"Massively parallel methods for deep reinforcement learning","volume":"abs 1507 4296","author":"nair","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"ref4","article-title":"Machine learning for interactive systems and robots: A brief introduction","author":"cuay\u00e1huitl","year":"2013","journal-title":"IJCAI Workshop on Machine Learning for Int Sys (MLIS)"},{"key":"ref3","article-title":"Training an interactive humanoid robot using multimodal deep reinforcement learning","volume":"abs 1611 8666","author":"cuay\u00e1huitl","year":"2016","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966275"},{"key":"ref5","article-title":"Deep reinforcement learning of dialogue policies with less weight updates","author":"cuay\u00e1huitl","year":"2017","journal-title":"Conference of the International Speech Communication Association"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/17538157.2016.1255627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324913000375"},{"key":"ref2","first-page":"109","author":"cuay\u00e1huitl","year":"2017","journal-title":"SimpleDS A simple deep reinforcement learning dialogue system"},{"key":"ref9","article-title":"Learning to play in a day: Faster deep reinforcement learning by optimality tightening","volume":"abs 1611 1606","author":"he","year":"2016","journal-title":"CoRR"},{"key":"ref1","article-title":"Robot learning from verbal interaction: A brief survey","author":"cuay\u00e1huitl","year":"2015","journal-title":"4th International Symposium on New Frontiers in HRI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref21","article-title":"Prioritized experience replay","volume":"abs 1511 5952","author":"schaul","year":"2015","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesv\u00e1ri","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref23","article-title":"Multimodal learning with deep boltzmann machines","volume":"15","author":"srivastava","year":"2014","journal-title":"J of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2004.03.011"}],"event":{"name":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","start":{"date-parts":[[2017,11,15]]},"location":"Birmingham","end":{"date-parts":[[2017,11,17]]}},"container-title":["2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8215882\/8239529\/08246959.pdf?arnumber=8246959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T00:33:42Z","timestamp":1660264422000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8246959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2017.8246959","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}