{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:23Z","timestamp":1760245043438,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,8]]},"DOI":"10.1109\/devlrn.2013.6652559","type":"proceedings-article","created":{"date-parts":[[2013,11,11]],"date-time":"2013-11-11T19:56:15Z","timestamp":1384199775000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["Emergence of flexible prediction-based discrete decision making and continuous motion generation through actor-Q-learning"],"prefix":"10.1109","author":[{"given":"Katsunari","family":"Shibata","sequence":"first","affiliation":[]},{"given":"Kenta","family":"Goto","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","first-page":"318","article-title":"Learning internal representation by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1002\/scj.10207"},{"key":"18","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","article-title":"Neuronlike adaptive elements can solve difficult learning control problems","volume":"13","author":"barto","year":"1983","journal-title":"IEEE Trans on Systems Man and Cybernetics"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/437654"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"16"},{"key":"13","first-page":"500","article-title":"Reinforcement learning in Markovian and non-Markovian environments","volume":"3","author":"schmidhuber","year":"1991","journal-title":"Advances in neural information processing systems"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00214-9"},{"key":"11","article-title":"Acquisition of Deterministic Exploration and Purposive Memory through Reinforcement Learning with a Recurrent Neural Network","author":"goto","year":"2010","journal-title":"Proc of SICE Annual Conf"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033394"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.5772\/13443"},{"journal-title":"Reinforcement Learning An Introduction A Bradford Book","year":"1998","author":"sutton","key":"20"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90053-M"},{"key":"1","first-page":"147","article-title":"Cognitive wheels: The frame problem of ai","author":"dennett","year":"1984","journal-title":"The Philosophy of Artificial Intelligence"},{"key":"10","first-page":"755","volume":"5506","author":"utsunomiya","year":"2009","journal-title":"Contextual Behavior and Internal Representations Acquired by Reinforcement Learning with A Recurrent Neural Network in A Continuous State and Action Space Task Advances in Neuro-Information Processing LNCS"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/BF02471125"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1163\/156855307781389365"},{"key":"5","first-page":"837","article-title":"Q-Learning with Recurrent Neural Networks as a Controller for the Inverted Pendulum Problem","volume":"98","author":"onat","year":"1998","journal-title":"Proc ICONIP"},{"key":"4","first-page":"271","article-title":"Reinforcement learning with hidden states","volume":"2","author":"lin","year":"1993","journal-title":"From Animals to Animats"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/3-211-27389-1_117"},{"key":"8","first-page":"430","article-title":"A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations","author":"bakker","year":"2003","journal-title":"Proc of IROS"}],"event":{"name":"2013 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","start":{"date-parts":[[2013,8,18]]},"location":"Osaka, Japan","end":{"date-parts":[[2013,8,22]]}},"container-title":["2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6645681\/6652520\/06652559.pdf?arnumber=6652559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T01:45:23Z","timestamp":1498095923000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6652559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2013.6652559","relation":{},"subject":[],"published":{"date-parts":[[2013,8]]}}}