{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T07:05:51Z","timestamp":1770015951639,"version":"3.49.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319416489","type":"print"},{"value":"9783319416496","type":"electronic"}],"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_2","type":"book-chapter","created":{"date-parts":[[2016,6,25]],"date-time":"2016-06-25T23:40:33Z","timestamp":1466898033000},"page":"12-22","source":"Crossref","is-referenced-by-count":12,"title":["Avoiding Wireheading with Value Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Tom","family":"Everitt","sequence":"first","affiliation":[]},{"given":"Marcus","family":"Hutter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,6,25]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: ICML, pp. 1\u20138 (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"2_CR2","unstructured":"Amin, K., Singh, S.: Towards resolving unidentifiability in inverse reinforcement learning (2016). http:\/\/arXiv.org\/abs\/1601.06569"},{"key":"2_CR3","unstructured":"Armstrong, S.: Motivated value selection for artificial agents. In: Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 12\u201320 (2015)"},{"key":"2_CR4","unstructured":"Bostrom, N.: Hail mary, value porosity, and utility diversification. Technical report, Oxford University (2014a)"},{"key":"2_CR5","unstructured":"Bostrom, N.: Superintelligence: Paths, Dangers, Strategies. Oxford University Press, New York (2014b)"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/978-3-642-22887-2_35","volume-title":"Artificial General Intelligence","author":"D Dewey","year":"2011","unstructured":"Dewey, D.: Learning what to value. In: Schmidhuber, J., Th\u00f3risson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol. 6830, pp. 309\u2013314. Springer, Heidelberg (2011)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Evans, O., Stuhlmuller, A., Goodman, N.D.: Learning the preferences of ignorant, inconsistent agents. In: AAAI 2016 (2016)","DOI":"10.1609\/aaai.v30i1.10010"},{"key":"2_CR8","unstructured":"Everitt, T., Filan, D., Daswani, M., Hutter, M.: Self-modification of policy and utility function in rational agents. In: Steunebrink, B., et al. (eds.) AGI 2016. LNAI, vol. 9782, pp. 1\u201311. Springer, Heidelberg (2016). http:\/\/arXiv.org\/abs\/1605.03142"},{"key":"2_CR9","unstructured":"Everitt, T., Hutter, M.: Avoiding wireheading with value reinforcement learning (2016). http:\/\/arXiv.org\/abs\/1605.03143"},{"issue":"1","key":"2_CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2478\/v10229-011-0013-5","volume":"3","author":"B Hibbard","year":"2012","unstructured":"Hibbard, B.: Model-based utility functions. J. Artif. General Intell. 3(1), 1\u201324 (2012)","journal-title":"J. Artif. General Intell."},{"key":"2_CR11","unstructured":"Kurzweil, R.: The Singularity Is Near. Viking Press, New York (2005)"},{"key":"2_CR12","unstructured":"Ng, A., Russell, S.: Algorithms for inverse reinforcement learning. In: ICML pp. 663\u2013670 (2000)"},{"key":"2_CR13","unstructured":"Nozick, R.: Anarchy, State, and Utopia. Basic Books, New York (1974)"},{"key":"2_CR14","unstructured":"Omohundro, S.M.: The basic AI drives. In: AGI-08. vol. 171, pp. 483\u2013493. IOS Press (2008)"},{"key":"2_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/978-3-642-22887-2_2","volume-title":"Artificial General Intelligence","author":"M Ring","year":"2011","unstructured":"Ring, M., Orseau, L.: Delusion, survival, and intelligent agents. In: Schmidhuber, J., Th\u00f3risson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol. 6830, pp. 11\u201320. Springer, Heidelberg (2011)"},{"key":"2_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1007\/978-3-319-21365-1_16","volume-title":"Artificial General Intelligence","author":"CE Sezener","year":"2015","unstructured":"Sezener, C.E.: Inferring human values for safe AGI design. In: Bieger, J., Goertzel, B., Potapov, A. (eds.) AGI 2015. LNCS, vol. 9205, pp. 152\u2013155. Springer, Heidelberg (2015)"},{"key":"2_CR17","unstructured":"Sinnott-Armstrong, W.: Consequentialism. In: Zalta, E.N. (ed.) The Stanford Encyclopedia of Philosophy. Winter 2015 edn. (2015)"},{"key":"2_CR18","unstructured":"Soares, N.: The value learning problem. Technical report, MIRI (2015)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)","DOI":"10.1109\/TNN.1998.712192"}],"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_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T05:17:50Z","timestamp":1656739070000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41649-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319416489","9783319416496"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41649-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}