{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:24:48Z","timestamp":1745360688556},"publisher-location":"Cham","reference-count":23,"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_1","type":"book-chapter","created":{"date-parts":[[2016,6,25]],"date-time":"2016-06-25T23:40:33Z","timestamp":1466898033000},"page":"1-11","source":"Crossref","is-referenced-by-count":7,"title":["Self-Modification of Policy and Utility Function in Rational Agents"],"prefix":"10.1007","author":[{"given":"Tom","family":"Everitt","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Filan","sequence":"additional","affiliation":[]},{"given":"Mayank","family":"Daswani","sequence":"additional","affiliation":[]},{"given":"Marcus","family":"Hutter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,6,25]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bird, J., Layzell, P.: The evolved radio and its implications for modelling the evolution of novel sensors. In: CEC-02, pp. 1836\u20131841 (2002)","DOI":"10.1109\/CEC.2002.1004522"},{"key":"1_CR2","volume-title":"Superintelligence: Paths, Dangers Strategies","author":"N Bostrom","year":"2014","unstructured":"Bostrom, N.: Superintelligence: Paths, Dangers Strategies. Oxford University Press, Oxford (2014)"},{"key":"1_CR3","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":"1_CR4","unstructured":"Everitt, T., Filan, D., Daswani, M., Hutter, M.: Self-modification of policy and utility function in rational agents. Technical report (2016). arXiv:1605.03142"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Everitt, T., Hutter, M.: Avoiding wireheading with value reinforcement learning. In: Steunebrink, B., et al. (eds.) AGI 2016, LNAI 9782, pp. 12\u201322 (2016)","DOI":"10.1007\/978-3-319-41649-6_2"},{"issue":"1","key":"1_CR6","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. Gen. Intell. Res. 3(1), 1\u201324 (2012)","journal-title":"J. Artif. Gen. Intell. Res."},{"key":"1_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/b138233","volume-title":"Universal Artificial Intelligence","author":"M Hutter","year":"2005","unstructured":"Hutter, M.: Universal Artificial Intelligence. Springer, Heidelberg (2005)"},{"key":"1_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/978-3-319-11662-4_14","volume-title":"Algorithmic Learning Theory","author":"M Hutter","year":"2014","unstructured":"Hutter, M.: Extreme state aggregation beyond MDPs. In: Auer, P., Clark, A., Zeugmann, T., Zilles, S. (eds.) ALT 2014. LNCS, vol. 8776, pp. 185\u2013199. Springer, Heidelberg (2014)"},{"issue":"1\u20132","key":"1_CR9","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"issue":"4","key":"1_CR10","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/s11023-007-9079-x","volume":"17","author":"S Legg","year":"2007","unstructured":"Legg, S., Hutter, M.: Universal intelligence: a definition of machine intelligence. Mind. Mach. 17(4), 391\u2013444 (2007)","journal-title":"Mind. Mach."},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Leike, J., Lattimore, T., Orseau, L., Hutter, M.: Thompson sampling is asymptotically optimal in general environments. In: UAI-16 (2016)","DOI":"10.24963\/ijcai.2017\/688"},{"issue":"7540","key":"1_CR12","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"1_CR13","unstructured":"Omohundro, S.M.: The basic AI drives. In: AGI-08, pp. 483\u2013493. IOS Press (2008)"},{"key":"1_CR14","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.tcs.2013.09.025","volume":"519","author":"L Orseau","year":"2014","unstructured":"Orseau, L.: Universal knowledge-seeking agents. TCS 519, 127\u2013139 (2014)","journal-title":"TCS"},{"key":"1_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-642-22887-2_1","volume-title":"Artificial General Intelligence","author":"L Orseau","year":"2011","unstructured":"Orseau, L., Ring, M.: Self-modification and mortality in artificial agents. In: Schmidhuber, J., Th\u00f3risson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol. 6830, pp. 1\u201310. Springer, Heidelberg (2011)"},{"key":"1_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/978-3-642-35506-6_22","volume-title":"Artificial General Intelligence","author":"L Orseau","year":"2012","unstructured":"Orseau, L., Ring, M.: Space-time embedded intelligence. In: Bach, J., Goertzel, B., Ikl\u00e9, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 209\u2013218. Springer, Heidelberg (2012)"},{"key":"1_CR17","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":"1_CR18","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/978-3-540-68677-4_7","volume-title":"Artificial General Intelligence","author":"J Schmidhuber","year":"2007","unstructured":"Schmidhuber, J.: G\u00f6del machines: fully self-referential optimal universal self-improvers. In: Goertzel, B., Pennachin, C. (eds.) AGI-07, pp. 199\u2013226. Springer, Heidelberg (2007)"},{"issue":"7587","key":"1_CR19","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"1_CR20","unstructured":"Soares, N.: The value learning problem. Technical report MIRI (2015)"},{"key":"1_CR21","unstructured":"Soares, N., Fallenstein, B., Yudkowsky, E., Armstrong, S.: Corrigibility. In: AAAI Workshop on AI and Ethics, pp. 74\u201382 (2015)"},{"key":"1_CR22","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"1_CR23","doi-asserted-by":"crossref","DOI":"10.1201\/b18612","volume-title":"Artificial Super Intelligence: A Futuristic Approach","author":"RV Yampolskiy","year":"2015","unstructured":"Yampolskiy, R.V.: Artificial Super Intelligence: A Futuristic Approach. Chapman and Hall\/CRC, Boca Raton (2015)"}],"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_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T06:07:42Z","timestamp":1568095662000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41649-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319416489","9783319416496"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41649-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}