{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T01:19:57Z","timestamp":1770427197492,"version":"3.49.0"},"reference-count":28,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2001,7,1]],"date-time":"2001-07-01T00:00:00Z","timestamp":993945600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics and Autonomous Systems"],"published-print":{"date-parts":[[2001,7]]},"DOI":"10.1016\/s0921-8890(01)00113-0","type":"journal-article","created":{"date-parts":[[2002,10,31]],"date-time":"2002-10-31T21:12:04Z","timestamp":1036098724000},"page":"37-51","source":"Crossref","is-referenced-by-count":169,"title":["Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning"],"prefix":"10.1016","volume":"36","author":[{"given":"Jun","family":"Morimoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Doya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0921-8890(01)00113-0_BIB1","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/S0004-3702(99)00024-7","article-title":"RoboCup: Today and tomorrow\u2014What we have learned","volume":"110","author":"Asada","year":"1999","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB2","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/S0004-3702(99)00026-0","article-title":"Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development","volume":"110","author":"Asada","year":"1999","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB3","unstructured":"P. Dayan, G.E. Hinton, Feudal reinforcement learning, in: Advances in Neural Information Processing Systems, Vol. 5, Morgan Kaufmann, San Francisco, CA, 1993, pp. 271\u2013278."},{"key":"10.1016\/S0921-8890(01)00113-0_BIB4","doi-asserted-by":"crossref","unstructured":"B.L. Digney, Learning hierarchical control structures for multiple tasks and changing environments, in: Proceedings of the Fifth Conference on the Simulation of Adaptive Behavior, MIT Press, Cambridge, MA, 1998, pp. 321\u2013330.","DOI":"10.7551\/mitpress\/3119.003.0050"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB5","unstructured":"K. Doya, Efficient nonlinear control with actor\u2013tutor architecture, in: M.C. Mozer, M.I. Jordan, T. Petsche (Eds.), Advances in Neural Information Processing Systems, Vol. 9, MIT Press, Cambridge, MA, 1997, pp. 1012\u20131018."},{"issue":"1","key":"10.1016\/S0921-8890(01)00113-0_BIB6","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1162\/089976600300015961","article-title":"Reinforcement learning in continuous time and space","volume":"12","author":"Doya","year":"2000","journal-title":"Neural Computation"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB7","doi-asserted-by":"crossref","unstructured":"M. Inaba, I. Igarashi, K. Kagami, I. Hirochika, A 35 DOF humanoid that can coordinate arms and legs in standing up, reaching and grasping an object, in: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS\u201996), Osaka, Japan, Vol. 1, 1996, pp. 29\u201336.","DOI":"10.1109\/IROS.1996.570622"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB8","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","article-title":"Hierarchical mixtures of experts and the EM algorithm","volume":"6","author":"Jacobs","year":"1994","journal-title":"Neural Computation"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB9","doi-asserted-by":"crossref","unstructured":"F. Kanehiro, M. Inaba, H. Inoue, Development of a two-armed bipedal robot that can walk and carry objects, in: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS\u201996), Osaka, Japan, Vol. 1, 1996, pp. 23\u201328.","DOI":"10.1109\/IROS.1996.570617"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB10","unstructured":"H. Kimura, S. Kobayashi, Efficient non-linear control by combining Q-learning with local linear controllers, in: Proceedings of the 16th International Conference on Machine Learning, Morgan Kaufmann, San Francisco, CA, 1999, pp. 210\u2013219."},{"key":"10.1016\/S0921-8890(01)00113-0_BIB11","doi-asserted-by":"crossref","unstructured":"F. Kirchner, Q-learning of complex behaviours on a six-legged walking machine, in: Proceedings of the Second EUROMICRO Workshop on Advanced Mobile Robots, 1997, pp. 51\u201358.","DOI":"10.1109\/EURBOT.1997.633565"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB12","doi-asserted-by":"crossref","unstructured":"Y. Kuniyoshi, A. Nagakubo, Humanoid as a research vehicle into flexible complex interaction, in: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS\u201997), Grenoble, France, 1997.","DOI":"10.1109\/IROS.1997.655104"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB13","unstructured":"P. Maes, R.A. Brooks, Learning to coordinate behaviors, in: Proceedings of AAAI\u201990, Boston, MA, 1990, pp. 796\u2013802."},{"key":"10.1016\/S0921-8890(01)00113-0_BIB14","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S0921-8890(96)00068-1","article-title":"Learning social behaviors","volume":"20","author":"Mataric","year":"1997","journal-title":"Robotics and Autonomous Systems"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB15","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1162\/neco.1989.1.2.281","article-title":"Fast learning in networks of locally-tuned processing units","volume":"1","author":"Moody","year":"1989","journal-title":"Neural Computation"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB16","unstructured":"J. Morimoto, K. Doya, Hierarchical reinforcement learning of low-dimensional sub-goals and high-dimensional trajectories, in: Proceedings of the Fifth International Conference on Neural Information Processing, Burke, VA, Vol. 2, IOS Press, Amsterdam, 1998, pp. 850\u2013853."},{"key":"10.1016\/S0921-8890(01)00113-0_BIB17","doi-asserted-by":"crossref","unstructured":"J. Morimoto, K. Doya, Reinforcement learning of dynamic motor sequence: learning to stand up, in: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS\u201998), Victoria, BC, Vol. 3, Omni Press, 1998, pp. 1721\u20131726.","DOI":"10.1109\/IROS.1998.724846"},{"issue":"559","key":"10.1016\/S0921-8890(01)00113-0_BIB18","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1299\/kikaic.59.850","article-title":"Motion control of a robot composed of three serial-links with curved contour (2nd report, several motions of the robot)","volume":"59","author":"Nakakuki","year":"1993","journal-title":"Transactions of the Japan Society of Mechanical Engineers, Part C"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB19","doi-asserted-by":"crossref","unstructured":"M. Ortiz, P. Zufiria, Evaluation of reinforcement learning autonomous navigation systems for a NOMAD 200 mobile robot, in: Proceedings of the Third IFAC Symposium on Intelligent Autonomous Vehicles 1998 (IAV\u201998), 1998, pp. 309\u2013314.","DOI":"10.1016\/S1474-6670(17)44103-6"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB20","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/BF00114731","article-title":"Incremental multi-step Q-learning","volume":"22","author":"Peng","year":"1996","journal-title":"Machine Learning"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB21","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/BF00992700","article-title":"Transfer of learning by composing solutions of elemental sequential tasks","volume":"8","author":"Singh","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB22","doi-asserted-by":"crossref","unstructured":"R.S. Sutton, A.G. Barto, Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, 1998.","DOI":"10.1109\/TNN.1998.712192"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB23","unstructured":"R.S. Sutton, D. Precup, S. Singh, Intra-option learning about temporary abstract actions, in: Proceedings of the 15th International Conference on Machine Learning, Madison, WI, 1998, pp. 556\u2013564."},{"key":"10.1016\/S0921-8890(01)00113-0_BIB24","doi-asserted-by":"crossref","unstructured":"Y. Takahashi, M. Asada, K. Hosoda, Reasonable performance in less learning time by real robot based on incremental state space segmentation, in: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS\u201996), Osaka, Japan, Vol. 3, 1996, pp. 1518\u20131524.","DOI":"10.1109\/IROS.1996.569014"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB25","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0921-8890(95)00005-Z","article-title":"Reinforcement learning of multiple tasks using a hierarchical CMAC architecture","volume":"15","author":"Tham","year":"1995","journal-title":"Robotics and Autonomous Systems"},{"issue":"2","key":"10.1016\/S0921-8890(01)00113-0_BIB26","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1177\/105971239700600202","article-title":"HQ-learning","volume":"6","author":"Wiering","year":"1997","journal-title":"Adaptive Behavior"},{"key":"10.1016\/S0921-8890(01)00113-0_BIB27","unstructured":"S. Yamada, A. Watanabe, M. Nakashima, Hybrid reinforcement learning and its application to biped robot control, in: Advances in Neural Information Processing Systems, Vol. 10, 1998, pp. 1071\u20131077."},{"key":"10.1016\/S0921-8890(01)00113-0_BIB28","doi-asserted-by":"crossref","unstructured":"T. Yamaguchi, M. Masubuchi, K. Fujihara, M. Yachica, Realtime reinforcement learning for a real robot in the real environment, in: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS\u201996), Osaka, Japan, Vol. 3, 1996, pp. 1321\u20131327.","DOI":"10.1109\/IROS.1996.568988"}],"container-title":["Robotics and Autonomous Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889001001130?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889001001130?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,12,31]],"date-time":"2023-12-31T19:09:32Z","timestamp":1704049772000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0921889001001130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,7]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2001,7]]}},"alternative-id":["S0921889001001130"],"URL":"https:\/\/doi.org\/10.1016\/s0921-8890(01)00113-0","relation":{},"ISSN":["0921-8890"],"issn-type":[{"value":"0921-8890","type":"print"}],"subject":[],"published":{"date-parts":[[2001,7]]}}}