{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:26:22Z","timestamp":1742912782490,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031199066"},{"type":"electronic","value":"9783031199073"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-19907-3_18","type":"book-chapter","created":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T06:07:32Z","timestamp":1673590052000},"page":"188-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning with\u00a0Information-Theoretic Actuation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9411-927X","authenticated-orcid":false,"given":"Elliot","family":"Catt","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3263-4097","authenticated-orcid":false,"given":"Marcus","family":"Hutter","sequence":"additional","affiliation":[]},{"given":"Joel","family":"Veness","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,14]]},"reference":[{"key":"18_CR1","volume-title":"Neuro-Dynamic Programming","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"18_CR2","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"18_CR3","unstructured":"Catt, E., Hutter, M., Veness, J.: Reinforcement learning with information-theoretic actuation. arXiv preprint arXiv:2109.15147 (2021)"},{"key":"18_CR4","volume-title":"Elements of Information Theory","author":"TM Cover","year":"1999","unstructured":"Cover, T.M.: Elements of Information Theory. Wiley, New York (1999)"},{"key":"18_CR5","unstructured":"Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K.O., Clune, J.: Go-explore: a new approach for hard-exploration problems (2021)"},{"key":"18_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/978-3-540-39624-6_24","volume-title":"Algorithmic Learning Theory","author":"M Hutter","year":"2003","unstructured":"Hutter, M.: On the existence and convergence of computable universal priors. In: Gavald\u00e1, R., Jantke, K.P., Takimoto, E. (eds.) ALT 2003. LNCS (LNAI), vol. 2842, pp. 298\u2013312. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-39624-6_24"},{"key":"18_CR7","unstructured":"Janner, M., Li, Q., Levine, S.: Reinforcement learning as one big sequence modeling problem (2021)"},{"key":"18_CR8","unstructured":"Milan, K., et al.: The forget-me-not process. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29. Curran Associates, Inc. (2016)"},{"issue":"7540","key":"18_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"18_CR10","unstructured":"Ortega, P., et al.: Meta-learning of sequential strategies (2019)"},{"issue":"2","key":"18_CR11","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1147\/rd.232.0149","volume":"23","author":"J Rissanen","year":"1979","unstructured":"Rissanen, J., Langdon, G.G.: Arithmetic coding. IBM J. Res. Dev. 23(2), 149\u2013162 (1979)","journal-title":"IBM J. Res. Dev."},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1145\/1577069.1755867","volume":"10","author":"A Strehl","year":"2009","unstructured":"Strehl, A., Li, L., Littman, M.: Reinforcement learning in finite MDPs: PAC analysis. J. Mach. Learn. Res. 10, 2413\u20132444 (2009). https:\/\/doi.org\/10.1145\/1577069.1755867","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"1","key":"18_CR14","first-page":"1","volume":"4","author":"C Szepesv\u00e1ri","year":"2010","unstructured":"Szepesv\u00e1ri, C.: Algorithms for reinforcement learning. Synth. Lect. Artif. Intell. Mach. Learn. 4(1), 1\u2013103 (2010)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"18_CR15","unstructured":"Veness, J., et al.: Gated linear networks. arXiv preprint arXiv:1910.01526 (2019)"},{"issue":"6","key":"18_CR16","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1145\/214762.214771","volume":"30","author":"IH Witten","year":"1987","unstructured":"Witten, I.H., Neal, R.M., Cleary, J.G.: Arithmetic coding for data compression. Commun. ACM 30(6), 520\u2013540 (1987)","journal-title":"Commun. ACM"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19907-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T07:05:34Z","timestamp":1673593534000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19907-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031199066","9783031199073"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19907-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"agi2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/agi-conf.org\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"61","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,54","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13 additional posters were included","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}