{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T09:27:52Z","timestamp":1759483672579},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319416489"},{"type":"electronic","value":"9783319416496"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-41649-6_26","type":"book-chapter","created":{"date-parts":[[2016,6,25]],"date-time":"2016-06-25T19:40:33Z","timestamp":1466883633000},"page":"258-261","source":"Crossref","is-referenced-by-count":6,"title":["Introspective Agents: Confidence Measures for General Value Functions"],"prefix":"10.1007","author":[{"given":"Craig","family":"Sherstan","sequence":"first","affiliation":[]},{"given":"Adam","family":"White","sequence":"additional","affiliation":[]},{"given":"Marlos C.","family":"Machado","sequence":"additional","affiliation":[]},{"given":"Patrick M.","family":"Pilarski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,6,25]]},"reference":[{"key":"26_CR1","unstructured":"Sutton, R.S., Modayil, J., Delp, M., Degris, T., Pilarski, P.M., White, A., Precup, D.: Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction categories and subject descriptors. In: International Conference on Autonomous Agents and Multi-Agent Systems, pp. 761\u2013768 (2011)"},{"key":"26_CR2","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1177\/1059712313511648","volume":"22","author":"J Modayil","year":"2014","unstructured":"Modayil, J., White, A., Sutton, R.S.: Multi-timescale nexting in a reinforcement learning robot. Adapt. Behav. 22, 146\u2013160 (2014)","journal-title":"Adapt. Behav."},{"key":"26_CR3","unstructured":"Edwards, A.L., Dawson, M.R., Hebert, J.S., Sherstan, C., Sutton, R.S., Chan, K.M., Pilarski, P.M.: Application of real-time machine learning to myoelectric prosthesis control: A case series in adaptive switching. Prosthet. Orthot. Int., published online ahead of print, pp. 1\u20139 (2015)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Sherstan, C., Modayil, J., Pilarski, P.M.: A collaborative approach to the simultaneous multi-joint control of a prosthetic arm. In: International Conference on Rehabilitation Robotics, Singapore, Singapore, pp. 13\u201318 (2015)","DOI":"10.1109\/ICORR.2015.7281168"},{"key":"26_CR5","volume-title":"Surfing Uncertainty: Prediction, Action, and the Embodied Mind","author":"A Clark","year":"2015","unstructured":"Clark, A.: Surfing Uncertainty: Prediction, Action, and the Embodied Mind. Oxford University Press, New York (2015)"},{"issue":"4","key":"26_CR6","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1109\/TSMCB.2008.920231","volume":"38","author":"MA Wiering","year":"2008","unstructured":"Wiering, M.A., van Hasselt, H.: Ensemble algorithms in reinforcement learning. IEEE Trans. Syst. Man, Cybern. Part B Cybern. 38(4), 930\u2013936 (2008)","journal-title":"IEEE Trans. Syst. Man, Cybern. Part B Cybern."},{"key":"26_CR7","unstructured":"White, A.: Developing a predictive approach to knowledge. Ph.D. Thesis. University of Alberta (2015)"},{"key":"26_CR8","unstructured":"Rafols, E.J., Ring, M.B., Sutton, R.S., Tanner, B.: Using predictive representations to improve generalization in reinforcement learning. In: International Joint Conference on Artificial Intelligence, pp. 835\u2013840 (2005)"},{"key":"26_CR9","unstructured":"Schaul, T., Ring, M.: Better generalization with forecasts. In: International Joint Conference on Artificial Intelligence, Beijing, China, pp. 1656\u20131662 (2013)"},{"key":"26_CR10","unstructured":"Littman, M.L., Sutton, R.S., Singh, S.: Predictive representations of state. In: Advances in Neural Information Processing Systems 14, pp. 1555\u20131561 (2001)"},{"key":"26_CR11","unstructured":"Sherstan, C.: Towards Prosthetic Arms as Wearable Intelligent Robots. MSc Thesis. University of Alberta (2015)"},{"key":"26_CR12","unstructured":"White, M., White, A.: Interval estimation for reinforcement-learning algorithms in continuous-state domains. In: Advances in Neural Information Processing Systems 23, pp. 2433\u20132441 (2010)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Curious model-building control systems. In: IEEE International Joint Conference on Neural Networks, Singapore, Singapore, Singapore, pp. 1458\u20131463 (1991)","DOI":"10.1109\/IJCNN.1991.170605"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-41649-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T13:09:33Z","timestamp":1498309773000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41649-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319416489","9783319416496"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41649-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}