{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T06:26:07Z","timestamp":1749450367328,"version":"3.40.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319213644"},{"type":"electronic","value":"9783319213651"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-21365-1_24","type":"book-chapter","created":{"date-parts":[[2015,7,14]],"date-time":"2015-07-14T04:07:08Z","timestamp":1436846828000},"page":"231-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Definition of Happiness for Reinforcement Learning Agents"],"prefix":"10.1007","author":[{"given":"Mayank","family":"Daswani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Leike","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,15]]},"reference":[{"unstructured":"Bostrom, N.: Superintelligence: Paths, Dangers. Oxford University Press, Strategies (2014)","key":"24_CR1"},{"unstructured":"Brickman, P., Campbell, D.T.: Hedonic relativism and planning the good society. Adaptation-Level Theory, pp. 287\u2013305 (1971)","key":"24_CR2"},{"key":"24_CR3","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1037\/0022-3514.36.8.917","volume":"36","author":"P Brickman","year":"1978","unstructured":"Brickman, P., Coates, D., Janoff-Bulman, R.: Lottery winners and accident victims: Is happiness relative? Journal of Personality and Social Psychology 36, 917 (1978)","journal-title":"Journal of Personality and Social Psychology"},{"doi-asserted-by":"crossref","unstructured":"Daswani, M., Leike, J.: A definition of happiness for reinforcement learning agents. Technical report, Australian National University (2015). http:\/\/arxiv.org\/abs\/1505.04497","key":"24_CR4","DOI":"10.1007\/978-3-319-21365-1_24"},{"key":"24_CR5","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1037\/0003-066X.61.4.305","volume":"61","author":"E Diener","year":"2006","unstructured":"Diener, E., Lucas, R.E., Scollon, C.N.: Beyond the hedonic treadmill: Revising the adaptation theory of well-being. American Psychologist 61, 305 (2006)","journal-title":"American Psychologist"},{"unstructured":"Jacobs, E., Broekens, J., Jonker, C.: Joy, distress, hope, and fear in reinforcement learning. In: Conference on Autonomous Agents and Multiagent Systems, pp. 1615\u20131616 (2014)","key":"24_CR6"},{"key":"24_CR7","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.jmp.2008.12.005","volume":"53","author":"Y Niv","year":"2009","unstructured":"Niv, Y.: Reinforcement learning in the brain. Journal of Mathematical Psychology 53, 139\u2013154 (2009)","journal-title":"Journal of Mathematical Psychology"},{"doi-asserted-by":"crossref","unstructured":"Rutledge, R.B., Skandali, N., Dayan, P., Dolan, R.J.: A computational and neural model of momentary subjective well-being. In: Proceedings of the National Academy of Sciences (2014)","key":"24_CR8","DOI":"10.1073\/pnas.1407535111"},{"key":"24_CR9","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TAMD.2010.2056368","volume":"2","author":"J Schmidhuber","year":"2010","unstructured":"Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation (1990\u20132010). IEEE Transactions on Autonomous Mental Development. 2, 230\u2013247 (2010)","journal-title":"IEEE Transactions on Autonomous Mental Development."},{"unstructured":"Sutton, R., Barto, A.: Time-derivative models of Pavlovian reinforcement. In: Learning and Computational Neuroscience: Foundations of Adaptive Networks, pp. 497\u2013537. MIT Press (1990)","key":"24_CR10"},{"doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)","key":"24_CR11","DOI":"10.1109\/TNN.1998.712192"},{"unstructured":"Tomasik, B.: Do artificial reinforcement-learning agents matter morally? Technical report, Foundational Research Institute (2014). http:\/\/arxiv.org\/abs\/1410.8233","key":"24_CR12"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21365-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T13:31:29Z","timestamp":1674567089000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-21365-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319213644","9783319213651"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21365-1_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"15 July 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}