{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:43:50Z","timestamp":1757702630264,"version":"3.40.3"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031479571"},{"type":"electronic","value":"9783031479588"}],"license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-47958-8_16","type":"book-chapter","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T18:01:56Z","timestamp":1700071316000},"page":"254-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning One Abstract Bit at\u00a0a\u00a0Time Through Self-invented Experiments Encoded as\u00a0Neural Networks"],"prefix":"10.1007","author":[{"given":"Vincent","family":"Herrmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis","family":"Kirsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"16_CR1","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. CoRR abs\/1912.06680 (2019). http:\/\/arxiv.org\/abs\/1912.06680"},{"key":"16_CR2","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. Preprint arXiv:1808.04355 (2018)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Faccio, F., Herrmann, V., Ramesh, A., Kirsch, L., Schmidhuber, J.: Goal-conditioned generators of deep policies. arXiv preprint arXiv:2207.01570 (2022)","DOI":"10.1609\/aaai.v37i6.25912"},{"key":"16_CR4","unstructured":"Faccio, F., Kirsch, L., Schmidhuber, J.: Parameter-based value functions. Preprint arXiv:2006.09226 (2020)"},{"key":"16_CR5","unstructured":"Faccio, F., Ramesh, A., Herrmann, V., Harb, J., Schmidhuber, J.: General policy evaluation and improvement by learning to identify few but crucial states. arXiv preprint arXiv:2207.01566 (2022)"},{"key":"16_CR6","unstructured":"Fedorov, V.V.: Theory of Optimal Experiments. Academic Press, Cambridge (1972)"},{"issue":"10","key":"16_CR7","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451\u20132471 (2000)","journal-title":"Neural Comput."},{"key":"16_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/978-3-642-32937-1_32","volume-title":"Parallel Problem Solving from Nature - PPSN XII","author":"F Gomez","year":"2012","unstructured":"Gomez, F., Koutn\u00edk, J., Schmidhuber, J.: Compressed network complexity search. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012. LNCS, vol. 7491, pp. 316\u2013326. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32937-1_32"},{"key":"16_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/11550907_61","volume-title":"Artificial Neural Networks: Formal Models and Their Applications \u2013 ICANN 2005","author":"F Gomez","year":"2005","unstructured":"Gomez, F., Schmidhuber, J.: Evolving modular fast-weight networks for control. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 383\u2013389. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11550907_61"},{"key":"16_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS), pp. 2672\u20132680, December 2014"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Multi-dimensional recurrent neural networks. In: Proceedings of the 17th International Conference on Artificial Neural Networks, September 2007","DOI":"10.1007\/978-3-540-74690-4_56"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for improved unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(5) (2009)","DOI":"10.1109\/TPAMI.2008.137"},{"key":"16_CR13","unstructured":"Ha, D., Dai, A., Le, Q.V.: Hypernetworks. arXiv preprint arXiv:1609.09106 (2016)"},{"key":"16_CR14","unstructured":"Harb, J., Schaul, T., Precup, D., Bacon, P.L.: Policy evaluation networks. arXiv preprint arXiv:2002.11833 (2020)"},{"issue":"1","key":"16_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1997.9.1.1","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Flat minima. Neural Comput. 9(1), 1\u201342 (1997)","journal-title":"Neural Comput."},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). based on TR FKI-207-95, TUM (1995)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"16_CR17","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1109\/JRPROC.1952.273898","volume":"40","author":"DA Huffman","year":"1952","unstructured":"Huffman, D.A.: A method for construction of minimum-redundancy codes. Proc. IRE 40, 1098\u20131101 (1952)","journal-title":"Proc. IRE"},{"key":"16_CR18","first-page":"7703","volume":"34","author":"K Irie","year":"2021","unstructured":"Irie, K., Schlag, I., Csord\u00e1s, R., Schmidhuber, J.: Going beyond linear transformers with recurrent fast weight programmers. Adv. Neural Inf. Process. Syst. 34, 7703\u20137717 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR19","unstructured":"Itti, L., Baldi, P.F.: Bayesian surprise attracts human attention. In: Advances in Neural Information Processing Systems (NIPS), vol. 19, pp. 547\u2013554. MIT Press, Cambridge, MA (2005)"},{"key":"16_CR20","first-page":"237","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. AI Res. 4, 237\u2013285 (1996)","journal-title":"J. AI Res."},{"key":"16_CR21","first-page":"14122","volume":"34","author":"L Kirsch","year":"2021","unstructured":"Kirsch, L., Schmidhuber, J.: Meta learning backpropagation and improving it. Adv. Neural Inf. Process. Syst. 34, 14122\u201314134 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR22","first-page":"1","volume":"1","author":"AN Kolmogorov","year":"1965","unstructured":"Kolmogorov, A.N.: Three approaches to the quantitative definition of information. Probl. Inf. Transm. 1, 1\u201311 (1965)","journal-title":"Probl. Inf. Transm."},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Koutn\u00edk, J., Gomez, F., Schmidhuber, J.: Evolving neural networks in compressed weight space. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 619\u2013626 (2010)","DOI":"10.1145\/1830483.1830596"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Koutn\u00edk, J., Cuccu, G., Schmidhuber, J., Gomez, F.: Evolving large-scale neural networks for vision-based reinforcement learning. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 1061\u20131068. ACM, Amsterdam, July 2013","DOI":"10.1145\/2463372.2463509"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 79\u201386 (1951)","DOI":"10.1214\/aoms\/1177729694"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Li, M., Vit\u00e1nyi, P.M.B.: An Introduction to Kolmogorov Complexity and its Applications (2nd edition). Springer, New York (1997). https:\/\/doi.org\/10.1007\/978-1-4757-2606-0","DOI":"10.1007\/978-1-4757-2606-0"},{"key":"16_CR27","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"16_CR28","unstructured":"Micheli, V., Alonso, E., Fleuret, F.: Transformers are sample efficient world models. arXiv preprint arXiv:2209.00588 (2022)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Andrychowicz, O.M., et al.: Learning dexterous in-hand manipulation. Int. J. Robot. Res. 39(1), 3\u201320 (2020)","DOI":"10.1177\/0278364919887447"},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/978-3-642-32375-1_13","volume-title":"Intrinsically Motivated Learning in Natural and Artificial Systems","author":"P-Y Oudeyer","year":"2013","unstructured":"Oudeyer, P.-Y., Baranes, A., Kaplan, F.: Intrinsically motivated learning of real-world sensorimotor skills with developmental constraints. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 303\u2013365. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-32375-1_13"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 16\u201317 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"16_CR32","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. arXiv preprint arXiv:1706.01905 (2017)"},{"key":"16_CR33","unstructured":"Ramesh, A., Kirsch, L., van Steenkiste, S., Schmidhuber, J.: Exploring through random curiosity with general value functions. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022)"},{"key":"16_CR34","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/0005-1098(78)90005-5","volume":"14","author":"J Rissanen","year":"1978","unstructured":"Rissanen, J.: Modeling by shortest data description. Automatica 14, 465\u2013471 (1978)","journal-title":"Automatica"},{"key":"16_CR35","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-540-87481-2_16","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"T R\u00fcckstie\u00df","year":"2008","unstructured":"R\u00fcckstie\u00df, T., Felder, M., Schmidhuber, J.: State-dependent exploration for policy gradient methods. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008. LNCS (LNAI), vol. 5212, pp. 234\u2013249. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-87481-2_16"},{"key":"16_CR36","unstructured":"Schlag, I., Irie, K., Schmidhuber, J.: Linear transformers are secretly fast weight programmers. In: International Conference on Machine Learning, pp. 9355\u20139366. PMLR (2021)"},{"key":"16_CR37","unstructured":"Schlag, I., Schmidhuber, J.: Learning to reason with third order tensor products. In: Advances in Neural Information Processing Systems (NIPS), pp. 9981\u20139993 (2018)"},{"key":"16_CR38","unstructured":"Schmidhuber, J.: Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments. Technical report FKI-126-90 (1990). http:\/\/people.idsia.ch\/~ juergen\/FKI-126-90_(revised)bw_ocr.pdf, Tech. Univ. Munich"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: An on-line algorithm for dynamic reinforcement learning and planning in reactive environments. In: Proceedings of the IEEE\/INNS International Joint Conference on Neural Networks, San Diego, vol. 2, pp. 253\u2013258 (1990)","DOI":"10.1109\/IJCNN.1990.137723"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Curious model-building control systems. In: Proceedings of the International Joint Conference on Neural Networks, Singapore, vol. 2, pp. 1458\u20131463. IEEE press (1991)","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Learning temporary variable binding with dynamic links. In: Proceedings of the International Joint Conference on Neural Networks, Singapore, vol. 3, pp. 2075\u20132079. IEEE (1991)","DOI":"10.1109\/IJCNN.1991.170693"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: A possibility for implementing curiosity and boredom in model-building neural controllers. In: Meyer, J.A., Wilson, S.W. (eds.) Proc. of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, pp. 222\u2013227. MIT Press\/Bradford Books (1991)","DOI":"10.7551\/mitpress\/3115.003.0030"},{"key":"16_CR43","unstructured":"Schmidhuber, J.: Reinforcement learning in Markovian and non-Markovian environments. In: Lippman, D.S., Moody, J.E., Touretzky, D.S. (eds.) Advances in Neural Information Processing Systems, vol. 3 (NIPS 3), pp. 500\u2013506. Morgan Kaufmann (1991)"},{"issue":"1","key":"16_CR44","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1162\/neco.1992.4.1.131","volume":"4","author":"J Schmidhuber","year":"1992","unstructured":"Schmidhuber, J.: Learning to control fast-weight memories: an alternative to recurrent nets. Neural Comput. 4(1), 131\u2013139 (1992)","journal-title":"Neural Comput."},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: On decreasing the ratio between learning complexity and number of time-varying variables in fully recurrent nets. In: Proceedings of the International Conference on Artificial Neural Networks, Amsterdam, pp. 460\u2013463. Springer (1993)","DOI":"10.1007\/978-1-4471-2063-6_110"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Discovering solutions with low Kolmogorov complexity and high generalization capability. In: Prieditis, A., Russell, S. (eds.) Machine Learning: Proceedings of the Twelfth International Conference, pp. 488\u2013496. Morgan Kaufmann Publishers, San Francisco, CA (1995)","DOI":"10.1016\/B978-1-55860-377-6.50067-0"},{"issue":"5","key":"16_CR47","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1016\/S0893-6080(96)00127-X","volume":"10","author":"J Schmidhuber","year":"1997","unstructured":"Schmidhuber, J.: Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Netw. 10(5), 857\u2013873 (1997)","journal-title":"Neural Netw."},{"key":"16_CR48","unstructured":"Schmidhuber, J.: What\u2019s interesting? Technical report IDSIA-35-97, IDSIA (1997). ftp:\/\/ftp.idsia.ch\/pub\/juergen\/interest.ps.gz; extended abstract in Proc. Snowbird\u201998, Utah, 1998; see also [50]"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Artificial curiosity based on discovering novel algorithmic predictability through coevolution. In: Angeline, P., Michalewicz, Z., Schoenauer, M., Yao, X., Zalzala, Z. (eds.) Congress on Evolutionary Computation, pp. 1612\u20131618. IEEE Press (1999)","DOI":"10.1109\/CEC.1999.785467"},{"key":"16_CR50","doi-asserted-by":"publisher","unstructured":"Schmidhuber, J.: Exploring the predictable. In: Ghosh, A., Tsuitsui, S. (eds.) Advances in Evolutionary Computing, pp. 579\u2013612. Springer, Berlin, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-642-18965-4_23","DOI":"10.1007\/978-3-642-18965-4_23"},{"issue":"4","key":"16_CR51","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1142\/S0129054102001291","volume":"13","author":"J Schmidhuber","year":"2002","unstructured":"Schmidhuber, J.: Hierarchies of generalized Kolmogorov complexities and nonenumerable universal measures computable in the limit. Int. J. Found. Comput. Sci. 13(4), 587\u2013612 (2002)","journal-title":"Int. J. Found. Comput. Sci."},{"key":"16_CR52","unstructured":"Schmidhuber, J.: Overview of artificial curiosity and active exploration, with links to publications since 1990 (2004). http:\/\/www.idsia.ch\/~juergen\/interest.html"},{"issue":"2","key":"16_CR53","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1080\/09540090600768658","volume":"18","author":"J Schmidhuber","year":"2006","unstructured":"Schmidhuber, J.: Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts. Connect. Sci. 18(2), 173\u2013187 (2006)","journal-title":"Connect. Sci."},{"key":"16_CR54","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/978-3-540-75488-6_3","volume-title":"Discovery Science","author":"J Schmidhuber","year":"2007","unstructured":"Schmidhuber, J.: Simple algorithmic principles of discovery, subjective beauty, selective attention, curiosity & creativity. In: Corruble, V., Takeda, M., Suzuki, E. (eds.) DS 2007. LNCS (LNAI), vol. 4755, pp. 26\u201338. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75488-6_3"},{"key":"16_CR55","unstructured":"Schmidhuber, J.: Compression progress: the algorithmic principle behind curiosity and creativity (with applications of the theory of humor) (2009). 40 min video of invited talk at Singularity Summit 2009, New York City: http:\/\/www.vimeo.com\/7441291. 10 min excerpts: http:\/\/www.youtube.com\/watch?v=Ipomu0MLFaI"},{"key":"16_CR56","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-642-02565-5_4","volume-title":"Anticipatory Behavior in Adaptive Learning Systems","author":"J Schmidhuber","year":"2009","unstructured":"Schmidhuber, J.: Driven by compression progress: a simple principle explains essential aspects of subjective beauty, novelty, surprise, interestingness, attention, curiosity, creativity, art, science, music, jokes. In: Pezzulo, G., Butz, M.V., Sigaud, O., Baldassarre, G. (eds.) ABiALS 2008. LNCS (LNAI), vol. 5499, pp. 48\u201376. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-02565-5_4"},{"issue":"3","key":"16_CR57","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 Trans. Auton. Ment. Dev. 2(3), 230\u2013247 (2010). https:\/\/doi.org\/10.1109\/TAMD.2010.2056368","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"16_CR58","unstructured":"Schmidhuber, J.: Overviews of artificial curiosity\/creativity and active exploration (with links to publications since 1990) (2012). http:\/\/www.idsia.ch\/~juergen\/interest.html, http:\/\/www.idsia.ch\/~juergen\/creativity.html"},{"key":"16_CR59","unstructured":"Schmidhuber, J.: Self-delimiting neural networks. Technical report. IDSIA-08-12, arXiv:1210.0118v1 [cs.NE], The Swiss AI Lab IDSIA (2012)"},{"key":"16_CR60","doi-asserted-by":"publisher","unstructured":"Schmidhuber, J.: PowerPlay: Training an increasingly general problem solver by continually searching for the simplest still unsolvable problem. Front. Psychol. (2013). https:\/\/doi.org\/10.3389\/fpsyg.2013.00313, (Based on arXiv:1112.5309v1 [cs.AI], 2011)","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"16_CR61","doi-asserted-by":"publisher","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015). https:\/\/doi.org\/10.1016\/j.neunet.2014.09.003, published online 2014; 888 references; based on TR arXiv:1404.7828 [cs.NE]","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"16_CR62","unstructured":"Schmidhuber, J.: On learning to think: algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models. Preprint arXiv:1511.09249 (2015)"},{"key":"16_CR63","unstructured":"Schmidhuber, J.: Artificial Curiosity & Creativity Since 1990\u201391. https:\/\/people.idsia.ch\/~juergen\/artificial-curiosity-since-1990.html (AI Blog, 2021), https:\/\/people.idsia.ch\/~juergen\/artificial-curiosity-since-1990.html"},{"key":"16_CR64","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991). Neural Networks (2020)","DOI":"10.1016\/j.neunet.2020.04.008"},{"key":"16_CR65","unstructured":"Schmidhuber, J.: Learning one abstract bit at a time through self-invented experiments. Unpublished Tech Report, IDSIA & NNAISENSE (2020)"},{"key":"16_CR66","doi-asserted-by":"crossref","unstructured":"Shannon, C.E.: A mathematical theory of communication (parts I and II). Bell Syst. Tech. J. XXVII, 379\u2013423 (1948)","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"issue":"6","key":"16_CR67","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/0893-9659(91)90080-F","volume":"4","author":"HT Siegelmann","year":"1991","unstructured":"Siegelmann, H.T., Sontag, E.D.: Turing computability with neural nets. Appl. Math. Lett. 4(6), 77\u201380 (1991)","journal-title":"Appl. Math. Lett."},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Singh, S., Barto, A.G., Chentanez, N.: Intrinsically motivated reinforcement learning. In: Advances in Neural Information Processing Systems (NIPS), vol. 17. MIT Press, Cambridge, MA (2005)","DOI":"10.21236\/ADA440280"},{"key":"16_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0019-9958(64)90223-2","volume":"7","author":"RJ Solomonoff","year":"1964","unstructured":"Solomonoff, R.J.: A formal theory of inductive inference. Part I. Inf. Control 7, 1\u201322 (1964)","journal-title":"Inf. Control"},{"key":"16_CR70","doi-asserted-by":"publisher","unstructured":"Srivastava, R.K., Steunebrink, B.R., Schmidhuber, J.: First experiments with PowerPlay. Neural Netw. 41, 130\u2013136 (2013). https:\/\/doi.org\/10.1016\/j.neunet.2013.01.022, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608013000373, special Issue on Autonomous Learning","DOI":"10.1016\/j.neunet.2013.01.022"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"van Steenkiste, S., Koutn\u00edk, J., Driessens, K., Schmidhuber, J.: A wavelet-based encoding for neuroevolution. In: Proceedings of the Genetic and Evolutionary Computation Conference 2016, pp. 517\u2013524. GECCO \u201916, ACM, New York, NY, USA (2016)","DOI":"10.1145\/2908812.2908905"},{"key":"16_CR72","unstructured":"Storck, J., Hochreiter, S., Schmidhuber, J.: Reinforcement driven information acquisition in non-deterministic environments. In: Proceedings of the International Conference on Artificial Neural Networks, Paris, vol. 2, pp. 159\u2013164. EC2 & Cie (1995)"},{"key":"16_CR73","doi-asserted-by":"crossref","unstructured":"Sun, Y., Gomez, F., Schmidhuber, J.: Planning to be surprised: optimal Bayesian exploration in dynamic environments. In: Proceedings of the Fourth Conference on Artificial General Intelligence (AGI), Google, Mountain View, CA (2011)","DOI":"10.1007\/978-3-642-22887-2_5"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"16_CR75","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 5998\u20136008 (2017)"},{"key":"16_CR76","unstructured":"Vemula, A., Sun, W., Bagnell, J.: Contrasting exploration in parameter and action space: a zeroth-order optimization perspective. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 2926\u20132935. PMLR (2019)"},{"issue":"7782","key":"16_CR77","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"issue":"2","key":"16_CR78","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1093\/comjnl\/11.2.185","volume":"11","author":"CS Wallace","year":"1968","unstructured":"Wallace, C.S., Boulton, D.M.: An information theoretic measure for classification. Comput. J. 11(2), 185\u2013194 (1968)","journal-title":"Comput. J."},{"key":"16_CR79","doi-asserted-by":"crossref","unstructured":"Wallace, C.S., Freeman, P.R.: Estimation and inference by compact coding. J. R. Stat. Soc. Ser. B 49(3), 240\u2013265 (1987)","DOI":"10.1111\/j.2517-6161.1987.tb01695.x"},{"key":"16_CR80","doi-asserted-by":"publisher","unstructured":"Wiering, M., van Otterlo, M.: Reinforcement Learning. Springer, Berlin, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3","DOI":"10.1007\/978-3-642-27645-3"},{"issue":"2","key":"16_CR81","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1093\/jigpal\/jzp049","volume":"18","author":"D Wierstra","year":"2010","unstructured":"Wierstra, D., Foerster, A., Peters, J., Schmidhuber, J.: Recurrent policy gradients. Log. J. IGPL 18(2), 620\u2013634 (2010)","journal-title":"Log. J. IGPL"},{"key":"16_CR82","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"issue":"6","key":"16_CR83","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":["Communications in Computer and Information Science","Active Inference"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47958-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T01:51:22Z","timestamp":1730512282000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47958-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,16]]},"ISBN":["9783031479571","9783031479588"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47958-8_16","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,16]]},"assertion":[{"value":"16 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Active Inference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwai-ws2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iwaiworkshop.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","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":"17","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":"50% - 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":"3","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":"3.5","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)"}}]}}